© 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. 40837
    Prev
    Next
    INDEX
    Explanations

    actual or certain

    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
    åıĪå¿«
    -0.09
    ewan
    -0.08
    -gnu
    -0.07
    åªĽ
    -0.07
    ertype
    -0.07
    ennon
    -0.07
    ewire
    -0.07
    yny
    -0.07
    .changed
    -0.07
    .opend
    -0.07
    POSITIVE LOGITS
    biot
    0.07
    _VENDOR
    0.07
    éĽĨåħ¨
    0.07
    宿
    0.07
     physical
    0.07
    ATO
    0.07
    fis
    0.06
    ÃīR
    0.06
    ideo
    0.06
    oth
    0.06
    Activations Density 0.008%

    No Known Activations