© 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. 18302
    Prev
    Next
    INDEX
    Explanations

    namely

    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¡
    -0.11
    åĬłæĭ¿å¤§
    -0.11
    aum
    -0.09
    à¹Į
    -0.08
    eus
    -0.08
    Ð¢Ðł
    -0.08
    isle
    -0.08
    borough
    -0.08
    æĢ§è´«è¡Ģ
    -0.08
    reich
    -0.08
    POSITIVE LOGITS
    常说çļĦ
    0.09
    çĦ¶æĺ¯
    0.09
    stående
    0.08
    íĿ¥
    0.08
    /from
    0.08
    ÑĥÑī
    0.08
    çĦ¶å¤§
    0.08
    æīĢè°ĵçļĦ
    0.08
    pects
    0.08
    வà¯ģà®®à¯į
    0.08
    Activations Density 0.003%

    No Known Activations