© 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. 39869
    Prev
    Next
    INDEX
    Explanations

    code formatting

    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
    pages
    -0.08
    tics
    -0.08
    ä¸Ģæī¹
    -0.07
    人æĹł
    -0.07
    Pages
    -0.07
    -pages
    -0.07
    idia
    -0.07
    ://%
    -0.07
    DbType
    -0.07
    /tty
    -0.07
    POSITIVE LOGITS
    æĢĴ
    0.07
    ä¸įå¼ĥ
    0.07
    çĦī
    0.07
    omie
    0.06
    inke
    0.06
    ĺ
    0.06
    ç±³å°Ķ
    0.06
    ilin
    0.06
    CPP
    0.06
    -show
    0.06
    Activations Density 0.336%

    No Known Activations