© 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. 57966
    Prev
    Next
    INDEX
    Explanations

    license identifiers and copyright notices

    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
     Rig
    -0.08
    istol
    -0.07
     ëĵ¤
    -0.06
    çķ¸
    -0.06
    ва
    -0.06
    ç§įç§įåİŁåĽł
    -0.06
    oleon
    -0.06
    RICT
    -0.06
    uten
    -0.06
    async
    -0.06
    POSITIVE LOGITS
    _SAFE
    0.07
    opak
    0.07
    SCAN
    0.07
    unce
    0.07
    çļĦçľ¼ç¥ŀ
    0.07
    ä¸į解
    0.07
    orro
    0.06
    IJ
    0.06
    ielle
    0.06
    屯
    0.06
    Activations Density 0.141%

    No Known Activations