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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84806
    Prev
    Next
    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash

    end-of-message delimiters in chat-style transcripts (especially the <|im_end|> token).

    oai_token-act-pair · gpt-5Triggered 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
    istles
    -0.08
    颇为
    -0.08
    csi
    -0.08
     Loans
    -0.07
    읿
    -0.07
    主帅
    -0.07
    有意思
    -0.07
    猾
    -0.07
    sad
    -0.06
    有多么
    -0.06
    POSITIVE LOGITS
    _managed
    0.07
    .look
    0.07
    Source
    0.07
    \">↵
    0.07
    🕷
    0.07
    _round
    0.07
    .elements
    0.06
    受
    0.06
     Three
    0.06
     waiting
    0.06
    Activations Density 0.149%

    No Known Activations