© 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. 20550
    Prev
    Next
    INDEX
    Explanations

    conjugate, replica, dissociation, admin panel, hacienda, supersymmetric, slash command, CA, cup length, epsilon

    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
     surprisingly
    -0.08
    æĢ»æĪIJ
    -0.07
    essar
    -0.07
    <|box_end|>
    -0.07
    æľīæĿ¡ä»¶
    -0.07
    gie
    -0.06
    onha
    -0.06
     bindActionCreators
    -0.06
    缴åĪ°çİ°åľ¨
    -0.06
    /proto
    -0.06
    POSITIVE LOGITS
    /
    0.09
    ablish
    0.08
    vé
    0.08
    uci
    0.08
    æĢ§æĪĸ
    0.07
    åĮĸå¤ĦçIJĨ
    0.07
    åıĭ们
    0.07
    ä¸Ģç«ł
    0.07
    -based
    0.07
    .cover
    0.07
    Activations Density 0.030%

    No Known Activations