© 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. 34060
    Prev
    Next
    INDEX
    Explanations

    C|1|2 combinations

    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
    é¦
    -0.08
    apon
    -0.07
    åĺĪ
    -0.07
    åıijæĶ¹
    -0.07
    spath
    -0.07
    ayi
    -0.07
    ysten
    -0.07
    çª
    -0.07
    åĭ¢
    -0.07
    çĮ¿
    -0.07
    POSITIVE LOGITS
    pch
    0.07
     gost
    0.06
    KET
    0.06
    æĿ¿
    0.06
     Gone
    0.06
    ryptography
    0.06
    çĻ½æ²Ļ
    0.06
    _VALUES
    0.06
    weed
    0.06
    åľ¨åľº
    0.06
    Activations Density 0.011%

    No Known Activations