© 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. 60831
    Prev
    Next
    INDEX
    Explanations

    code and scripts

    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
    isl
    -0.08
    ipated
    -0.07
    身åıĹ
    -0.06
    åħ·æľī
    -0.06
    à¸Ħม
    -0.06
    (symbol
    -0.06
    ä¸Ģ家
    -0.06
    symbol
    -0.06
    æĽ´åĬł
    -0.06
    apos
    -0.06
    POSITIVE LOGITS
    .Typed
    0.08
    çIJħ
    0.08
     Merdeka
    0.07
    à¹Ģà¸ķร
    0.07
    åĬłæĭī
    0.07
    ROTO
    0.07
    elat
    0.07
    .matcher
    0.07
    णà¥Ģ
    0.07
    à¸Ńยà¹Īาà¸ĩà¹Ħมà¹Īà¸ĸูà¸ģà¸ķà¹īà¸Ńà¸ĩ
    0.07
    Activations Density 0.001%

    No Known Activations