© 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. 32302
    Prev
    Next
    INDEX
    Explanations

    Matter of

    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
    :\\
    -0.07
    enan
    -0.07
    arra
    -0.07
    .setdefault
    -0.07
    ilig
    -0.07
    aucoup
    -0.07
    ordin
    -0.07
    entimes
    -0.06
    æŃ£è½¨
    -0.06
    åĽ½åįİ
    -0.06
    POSITIVE LOGITS
    éĺľ
    0.08
    enaar
    0.08
     sake
    0.07
    ä»ķæĸ¹
    0.07
    sons
    0.07
    ourse
    0.07
    ignment
    0.07
    bai
    0.07
     Hole
    0.06
    ZEN
    0.06
    Activations Density 0.026%

    No Known Activations