© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21612
    Prev
    Next
    INDEX
    Explanations

    step by step, year by year, side by side

    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
    asai
    -0.10
    esel
    -0.10
    arani
    -0.10
    amani
    -0.10
    aned
    -0.09
    ä¸ĢæľĿ
    -0.09
    aschen
    -0.09
    ateľ
    -0.09
    天çĽĸ
    -0.09
    æ¯ĭ庸
    -0.09
    POSITIVE LOGITS
    .
    0.07
    rix
    0.06
    oto
    0.06
    ,
    0.06
    cket
    0.05
    ÑĪем
    0.05
    åľ°åľ¨
    0.05
    è·¯
    0.05
     I
    0.05
    è¾Ľ
    0.05
    Activations Density 0.020%

    No Known Activations