© 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. 15433
    Prev
    Next
    INDEX
    Explanations

    spreadsheet cells

    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
    udu
    -0.08
    ä¸ī份
    -0.07
    sted
    -0.07
    ÅĤaw
    -0.07
    icum
    -0.07
    endus
    -0.07
     esaur
    -0.07
    æľ¬ç½ij转载
    -0.07
    onia
    -0.07
    è¾ľè´Ł
    -0.07
    POSITIVE LOGITS
    rows
    0.09
     row
    0.07
    row
    0.07
    -row
    0.06
    Ai
    0.06
    çŀ©
    0.06
    liest
    0.06
     matr
    0.06
    鸳鸯
    0.06
    Rows
    0.06
    Activations Density 0.003%

    No Known Activations