© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 83308
    Prev
    Next
    INDEX
    Explanations

    news snippets

    np_max-act · gemini-2.0-flash

    The neuron detects main finite verbs (auxiliaries and modals or other lexical verbs that serve as the sentence's primary predicate, signaling tense/aspect or modality).

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    indexes
    -0.07
    MBED
    -0.07
    炎热
    -0.07
    enticate
    -0.07
     paginate
    -0.07
    ichert
    -0.07
    鄚
    -0.07
     Melbourne
    -0.07
     Barker
    -0.07
    驱动
    -0.07
    POSITIVE LOGITS
     zostać
    0.07
     список
    0.07
     XI
    0.06
    addOn
    0.06
    .next
    0.06
    輸
    0.06
    新车
    0.06
    橞
    0.06
     finding
    0.06
    .DependencyInjection
    0.06
    Activations Density 0.422%

    No Known Activations