© 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. 58089
    Prev
    Next
    INDEX
    Explanations

    let us help

    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
    zar
    -0.07
    _beg
    -0.07
    èĩ³æѤ
    -0.07
    @\
    -0.07
    åı¦å¤ĸä¸Ģç§į
    -0.07
     priv
    -0.07
    elis
    -0.07
    ھا
    -0.07
    æĦıçļĦ
    -0.07
    este
    -0.06
    POSITIVE LOGITS
    cardo
    0.09
    omie
    0.08
    vern
    0.07
    åŁºæľ¬æ¦Ĥ念
    0.07
    ä¸į为人
    0.07
    kowa
    0.07
    å°ıçŁ¥è¯Ĩ
    0.07
    rud
    0.07
    acro
    0.07
    adro
    0.06
    Activations Density 0.008%

    No Known Activations