© 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. 16379
    Prev
    Next
    INDEX
    Explanations

    č notation

    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
    ansen
    -0.07
    gege
    -0.06
    =>
    -0.06
    à¬Ľ
    -0.06
    ä¾ĭ
    -0.06
     otherwise
    -0.06
    in
    -0.06
    å·²çĶ±
    -0.06
     Navy
    -0.06
    羣å®ŀ
    -0.06
    POSITIVE LOGITS
    容
    0.08
    âĢ¦]
    0.08
    ierer
    0.07
    å®ĺæĸ¹å¾®ä¿¡
    0.07
    å¹¹
    0.07
    åħ¨éĿ¢è´¯å½»èIJ½å®ŀ
    0.07
    _OFF
    0.07
    ipas
    0.07
    agl
    0.07
    è¿Ħ
    0.07
    Activations Density 0.038%

    No Known Activations