© 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. 39241
    Prev
    Next
    INDEX
    Explanations

    WEB offers

    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
    еÑģÑĮ
    -0.07
    æĸ°åĬłåĿ¡
    -0.06
     sums
    -0.06
    escu
    -0.06
    izzi
    -0.06
    zion
    -0.06
    wares
    -0.06
    heit
    -0.06
    tschaft
    -0.06
    ting
    -0.06
    POSITIVE LOGITS
    \xa
    0.08
    ä¸ĢæľĽ
    0.08
    jna
    0.07
    ä¸Ģåĵģ
    0.07
    osten
    0.07
    çĶ²çŃī
    0.07
    ranc
    0.07
    两åįĥ
    0.07
    ;amp
    0.07
    elp
    0.07
    Activations Density 0.057%

    No Known Activations