© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14528
    Prev
    Next
    INDEX
    Explanations

    AD: Meta, Sou, In, High, author

    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
    arn
    -0.07
    aka
    -0.07
    xx
    -0.07
    aks
    -0.06
    让
    -0.06
    ac
    -0.06
    ç²Ĺ
    -0.06
    ailed
    -0.06
    oon
    -0.06
    aat
    -0.06
    POSITIVE LOGITS
    asanya
    0.09
     noqa
    0.09
    å¢ħ
    0.08
    ersp
    0.08
    åħįè´¹åĴ¨è¯¢
    0.08
    翼翼
    0.08
     beker
    0.08
    <|box_end|>
    0.08
     rumpe
    0.08
     dikat
    0.07
    Activations Density 0.001%

    No Known Activations