© 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. 37915
    Prev
    Next
    INDEX
    Explanations

    polynomials with variables

    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
    ÃŃk
    -0.07
    ething
    -0.07
    ç¨ĭ度ä¸Ĭ
    -0.07
    erte
    -0.06
    iento
    -0.06
    _bbox
    -0.06
    鸣
    -0.06
     Tra
    -0.06
    åIJ¯
    -0.06
    onders
    -0.06
    POSITIVE LOGITS
    dale
    0.08
    MDB
    0.08
    idle
    0.07
    mdb
    0.07
    dma
    0.07
    trys
    0.07
    (Fl
    0.07
    azen
    0.07
    idget
    0.07
    vors
    0.07
    Activations Density 0.020%

    No Known Activations