© 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. 51704
    Prev
    Next
    INDEX
    Explanations

    issued, does, r, /, rocks, you, should, you, other

    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
     grav
    -0.07
    arkan
    -0.07
    æĺ¯ä¸Ģ个å¾Ī
    -0.06
    eram
    -0.06
    rotch
    -0.06
    [__
    -0.06
    askan
    -0.06
    uning
    -0.06
    elop
    -0.06
     herself
    -0.06
    POSITIVE LOGITS
     nÃło
    0.10
    /how
    0.10
     they
    0.10
     we
    0.08
    å·¥ä½ľå¼Ģå±ķ
    0.08
     они
    0.08
     jaki
    0.08
     ÙĪØ£ÙĬ
    0.08
     you
    0.08
     koju
    0.08
    Activations Density 0.289%

    No Known Activations