© 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. 58559
    Prev
    Next
    INDEX
    Explanations

    code identifiers followed by punctuation

    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
    èĮ¨
    -0.07
    -
    -0.06
    <|im_end|>
    -0.06
    memb
    -0.06
    ез
    -0.06
    /
    -0.06
    $(
    -0.06
    $\
    -0.06
     $(
    -0.06
    POSITIVE LOGITS
    ÙĬÙĦØ©
    0.08
    æĺ¯åŃ©åŃIJ
    0.08
    uste
    0.08
    usting
    0.08
    usercontent
    0.08
     rellen
    0.07
     ÂŃ
    0.07
    lage
    0.07
    icide
    0.07
    uttle
    0.07
    Activations Density 0.003%

    No Known Activations