© 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. 29469
    Prev
    Next
    INDEX
    Explanations

    modelget key id name model data

    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
    æĸ°åĬłåĿ¡
    -0.08
    çļĦãģ«
    -0.08
    åij³çļĦ
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    nya
    -0.07
    kev
    -0.06
    ively
    -0.06
    ित
    -0.06
    天边
    -0.06
    ense
    -0.06
    POSITIVE LOGITS
    halt
    0.08
    hone
    0.08
    gether
    0.08
    riors
    0.07
    esz
    0.07
    llib
    0.07
    vrier
    0.07
    Ù°
    0.07
    itage
    0.07
    Ø©
    0.07
    Activations Density 0.029%

    No Known Activations