© 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. 44954
    Prev
    Next
    INDEX
    Explanations

    .getStyle and requirements

    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
    agas
    -0.07
    uset
    -0.07
    asten
    -0.07
    obie
    -0.07
    ï¼Ĭ
    -0.06
     ìĺ¬
    -0.06
     ;-)
    -0.06
    ãĤ¸ãĤ¢
    -0.06
    ivor
    -0.06
    uge
    -0.06
    POSITIVE LOGITS
    使åħ¶
    0.07
    ys
    0.07
     INTEG
    0.07
    hern
    0.07
    ikh
    0.07
    让åħ¶
    0.06
    .getStyle
    0.06
    juk
    0.06
    大大
    0.06
    åĽłç´łçļĦå½±åĵį
    0.06
    Activations Density 0.238%

    No Known Activations