© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 125344
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    the neuron detects proper nouns, especially names of people or organizations.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Koh
    -0.07
    Clusters
    -0.07
    🐦
    -0.07
    _public
    -0.07
    อ
    -0.06
    ᒃ
    -0.06
     cuk
    -0.06
    -0.06
     Fonts
    -0.06
    🦋
    -0.06
    POSITIVE LOGITS
    .article
    0.07
    ailable
    0.07
    “They
    0.07
    돠
    0.07
    ưa
    0.06
    culo
    0.06
    יצו
    0.06
    月中旬
    0.06
    	trace
    0.06
    .normalized
    0.06
    Activations Density 0.104%

    No Known Activations