© 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. 62215
    Prev
    Next
    INDEX
    Explanations

    UNIX Timestamp

    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
    ä¸ĭå®ļ
    -0.07
    åľ¨ä¼Ĺå¤ļ
    -0.07
    åħ·æľīå¾Ī强çļĦ
    -0.07
    ç«Ļç«Ļ
    -0.07
    åĩĨ
    -0.07
    tü
    -0.07
    oly
    -0.07
    -ahead
    -0.07
     distinguished
    -0.07
    æ£Ģ
    -0.07
    POSITIVE LOGITS
    eler
    0.08
    <|fim_suffix|>
    0.07
    ðŁĺ
    0.07
    egur
    0.07
    ]['
    0.06
    pong
    0.06
    ÙĤرار
    0.06
    â
    0.06
    ['
    0.06
    //'
    0.06
    Activations Density 0.001%

    No Known Activations