© 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. 22651
    Prev
    Next
    INDEX
    Explanations

    CREATE TABLE, Sun Jun

    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
    lander
    -0.08
    elle
    -0.08
    æľ¬åĪĬ
    -0.07
     vota
    -0.07
    æķ¦
    -0.07
    忱
    -0.07
    宫ä¸Ń
    -0.07
    weig
    -0.07
    åIJīå°Ķ
    -0.07
    slag
    -0.07
    POSITIVE LOGITS
    awan
    0.07
    opter
    0.07
    oke
    0.07
    ize
    0.07
    å¾ĹçŁ¥
    0.06
    ä¸ĥåįģäºĮ
    0.06
    icarbon
    0.06
    Äģk
    0.06
    å¤©çľŁ
    0.06
    çĿ
    0.06
    Activations Density 0.001%

    No Known Activations