© 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. 51716
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    unki
    -0.08
    å¼±çļĦ
    -0.07
    emaker
    -0.07
    ä¸ī大
    -0.07
    çļĦ表éĿ¢
    -0.07
    orca
    -0.07
    kens
    -0.07
    ç¿ħ
    -0.07
    è¨
    -0.07
    nung
    -0.07
    POSITIVE LOGITS
    ä»İ鼶
    0.07
    æĢ»åı°
    0.07
    ä»İæĹł
    0.07
    ition
    0.07
    åĽ´
    0.07
    à¸Ļัà¸ļ
    0.07
    _GRAY
    0.06
    protobuf
    0.06
    åľį
    0.06
    å¾·å°Ķ
    0.06
    Activations Density 0.006%

    No Known Activations