© 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. 38902
    Prev
    Next
    INDEX
    Explanations

    code 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
    ç«£
    -0.07
    å¼ĢæĶ¾çļĦ
    -0.07
    anza
    -0.06
    acon
    -0.06
    utz
    -0.06
    езде
    -0.06
    Opens
    -0.06
    ιλ
    -0.06
    tro
    -0.06
    हित
    -0.06
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.08
    .Must
    0.08
    sos
    0.07
    unker
    0.07
    失èī²
    0.07
    nak
    0.07
    ä¸Ģä¸ĸ
    0.07
    bella
    0.07
    太çĻ½
    0.07
    çĭĤ
    0.07
    Activations Density 0.076%

    No Known Activations