© 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. 47459
    Prev
    Next
    INDEX
    Explanations

    code structure markers

    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
    mine
    -0.08
    hor
    -0.07
    Mine
    -0.07
    esp
    -0.07
    hre
    -0.07
    zee
    -0.06
    hr
    -0.06
     mostly
    -0.06
    ä¸ĢèĪ¬
    -0.06
    人æĢ§
    -0.06
    POSITIVE LOGITS
    æ·±æľī
    0.07
    venues
    0.07
    æľªåıĸå¾Ĺ
    0.07
     deliberately
    0.07
    żeli
    0.07
    ünd
    0.07
    åĭ¢
    0.07
    chnet
    0.07
    ilst
    0.07
    __/
    0.07
    Activations Density 0.001%

    No Known Activations