© 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. 24615
    Prev
    Next
    INDEX
    Explanations

    weight class

    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
    çĥ½
    -0.07
    зÑĮ
    -0.07
    stitution
    -0.06
    åijĬ
    -0.06
    çĤ¸
    -0.06
    åĪĨæ°´
    -0.06
    positions
    -0.06
    phin
    -0.06
    å°±æĺ¯è¿Ļ个
    -0.06
    éģ®
    -0.06
    POSITIVE LOGITS
    elry
    0.09
    olis
    0.09
    تÙħاÙĨ
    0.08
    ква
    0.08
    obot
    0.08
    è¿Ļ两ç§į
    0.08
     dak
    0.08
    第ä¸īç§į
    0.08
    人æĦı
    0.08
    astic
    0.07
    Activations Density 0.031%

    No Known Activations