© 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 EvalsExportsAPI 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. 16585
    Prev
    Next
    INDEX
    Explanations

    misspelled words

    np_max-act · gemini-2.0-flash

    This neuron detects text that contains many grammatical and spelling errors or instructions asking for intentionally poor/bad grammar.

    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
    svm
    -0.07
     vague
    -0.07
     tele
    -0.06
    빌
    -0.06
    Ba
    -0.06
    annies
    -0.06
    lookup
    -0.06
     sign
    -0.06
    Trees
    -0.06
     meantime
    -0.06
    POSITIVE LOGITS
    أسلحة
    0.08
    品类
    0.08
    _SENS
    0.08
     aftermarket
    0.07
     plutôt
    0.07
    (isolate
    0.07
    (animated
    0.07
     reopen
    0.07
     erot
    0.07
     calloc
    0.07
    Activations Density 0.258%

    No Known Activations