© 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. 31380
    Prev
    Next
    INDEX
    Explanations

    input, main, name, id, hash

    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
    igma
    -0.07
     clipping
    -0.07
    ÑĤопе
    -0.07
    erci
    -0.07
    bow
    -0.07
     blat
    -0.07
    upertino
    -0.07
    воÑĢо
    -0.07
    polis
    -0.07
    å°Ķå¾·
    -0.07
    POSITIVE LOGITS
    span
    0.06
    奸
    0.06
    éĹ·
    0.06
    æĥĬéĨĴ
    0.06
    *&
    0.06
    asian
    0.06
    á»į
    0.06
    arti
    0.06
    æĮ¤
    0.06
    "|
    0.06
    Activations Density 0.002%

    No Known Activations