© 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. 22095
    Prev
    Next
    INDEX
    Explanations

    Fair child

    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
    atter
    -0.08
    **”
    -0.08
    treff
    -0.07
    Ð¡Ð¡Ðł
    -0.07
    eldon
    -0.07
    aurus
    -0.07
    çĭ¬ç§Ģ
    -0.07
    ìĿ´ìĬ¤
    -0.07
    erma
    -0.07
     priori
    -0.07
    POSITIVE LOGITS
    æ¯Ľæ³½ä¸ľ
    0.08
    ness
    0.07
    thumb
    0.07
    ormsg
    0.06
    ArrayOf
    0.06
    !!:
    0.06
    lak
    0.06
    ä¸İ管çIJĨ
    0.06
    ä¸İæ²»çĸĹ
    0.06
    hin
    0.06
    Activations Density 0.082%

    No Known Activations