© 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. 31525
    Prev
    Next
    INDEX
    Explanations

    numbers and fractions

    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
    绣
    -0.08
    elj
    -0.07
     afore
    -0.07
    å®ļä¼ļ
    -0.06
    ç¥ŀéĢļ
    -0.06
    çĻ½åıij
    -0.06
    åĽ½å¼º
    -0.06
    å°±ä¸įåĨį
    -0.06
     accessed
    -0.06
    æĿŃ
    -0.06
    POSITIVE LOGITS
    ÑĨ
    0.07
    າàºĻ
    0.07
    rave
    0.07
    æĭĶ
    0.07
    adero
    0.06
    xCF
    0.06
    xCD
    0.06
    ä»»ä½ķ责任
    0.06
    è±ļ
    0.06
    missible
    0.06
    Activations Density 0.003%

    No Known Activations