© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 65024
    Prev
    Next
    INDEX
    Explanations

    declaration or english statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á»Ŀ
    -0.08
    anst
    -0.08
    å±ķå¼Ģåħ¨éĥ¨
    -0.08
    unky
    -0.08
     Lauderdale
    -0.08
    èĦļä¸ĭ
    -0.08
    æŁ¥çľĭåħ¨éĥ¨
    -0.07
    åIJįæĢĿ
    -0.07
    ennie
    -0.07
     zajÄĻ
    -0.07
    POSITIVE LOGITS
     inconsistent
    0.07
    模ç³Ĭ
    0.07
    æĦıåĽ¾
    0.07
     inconsist
    0.07
     Knob
    0.07
     ver
    0.07
     inconsistency
    0.07
     inconsistencies
    0.06
     reproduced
    0.06
     verschw
    0.06
    Activations Density 0.003%

    No Known Activations