© 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. 2216
    Prev
    Next
    INDEX
    Explanations

    case descriptions

    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
    /
    -0.06
    \
    -0.06
    el
    -0.06
    ac
    -0.06
    .define
    -0.06
    ine
    -0.06
    elo
    -0.06
    inc
    -0.06
    ↵
    -0.06
    POSITIVE LOGITS
    lahan
    0.09
     fras
    0.09
     helicopt
    0.08
    avanaugh
    0.08
     nost
    0.08
    xmax
    0.08
    ÑĦÑĥ
    0.08
    ciel
    0.08
    éĵºå¤©çĽĸ
    0.08
    à®´
    0.08
    Activations Density 0.002%

    No Known Activations