© 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. 2788
    Prev
    Next
    INDEX
    Explanations

    .pow, .map, .Encoding, .hashCode

    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¬Ĩ
    -0.09
    -Identifier
    -0.09
    ׳×Ķ
    -0.08
    笤
    -0.07
    ²
    -0.07
    UnitOfWork
    -0.07
    akest
    -0.07
    _bias
    -0.07
    ester
    -0.07
    ustering
    -0.07
    POSITIVE LOGITS
    еÑħ
    0.06
    atat
    0.06
     edition
    0.06
    çļĦå¤ĸ表
    0.06
    å¼ķ以为
    0.06
    zig
    0.06
    éĩijèĬ±
    0.06
     tap
    0.06
    ents
    0.06
    å±ŀæĢ§åĴĮ
    0.06
    Activations Density 0.005%

    No Known Activations