© 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. 63375
    Prev
    Next
    INDEX
    Explanations

    web addresses and abbreviations

    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
     ШаÑĢ
    -0.07
    inky
    -0.07
    REV
    -0.07
    TTY
    -0.07
    ancang
    -0.07
    specs
    -0.07
    æľĽè¿ľ
    -0.06
    bate
    -0.06
    à¸ļุรี
    -0.06
    ิà¸ķ
    -0.06
    POSITIVE LOGITS
    ç«ĭåĬŁ
    0.08
    estes
    0.07
    uai
    0.07
    åıĺéĢŁ
    0.07
    rypton
    0.07
    åħ¨ç§ij
    0.07
    jeti
    0.07
    è¿IJ
    0.06
     cok
    0.06
     GÅĤów
    0.06
    Activations Density 0.001%

    No Known Activations