© 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. 21271
    Prev
    Next
    INDEX
    Explanations

    dimensions and listings

    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
    æĪĸä¸İ
    -0.07
    ê¸°ë¡ľ
    -0.07
    è¡Įäºĭ
    -0.06
    åľ¨è§Ħå®ļ
    -0.06
    [c
    -0.06
    æĬĺä¸į
    -0.06
    &type
    -0.06
     Branco
    -0.06
     μή
    -0.06
    &view
    -0.06
    POSITIVE LOGITS
    =?,
    0.08
    amble
    0.08
    iders
    0.08
    ä¿©
    0.08
    ascar
    0.07
     ÐłÐ°Ð·Ñĥ
    0.07
    ãĢģ
    0.07
    uman
    0.07
    åİĭåĬĽå¤§
    0.07
    (Constructor
    0.07
    Activations Density 0.023%

    No Known Activations