© 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. 34527
    Prev
    Next
    INDEX
    Explanations

    $\int$ and \\ Earn

    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
    _NATIVE
    -0.08
    <|box_end|>
    -0.07
    лим
    -0.07
    tus
    -0.06
    denes
    -0.06
    achus
    -0.06
    æĿ¥ä¹ĭä¸įæĺĵ
    -0.06
    æĺİæĺ¾æıIJé«ĺ
    -0.06
    çĴŀ
    -0.06
    èĮ¨
    -0.06
    POSITIVE LOGITS
    selectAll
    0.08
     across
    0.08
    sel
    0.08
    éĻIJäºİ
    0.07
    éģįåıĬ
    0.07
    åĪ°å¤©
    0.07
    Ỽn
    0.07
    åĪ°åŃ¦æł¡
    0.07
    ancen
    0.07
     negli
    0.07
    Activations Density 0.002%

    No Known Activations