© 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. 33678
    Prev
    Next
    INDEX
    Explanations

    quasi followed by hyphen

    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
    åĬłæĭ¿å¤§
    -0.10
    æĿ¥å¾ĹåıĬ
    -0.09
    æĸ°åĬłåĿ¡
    -0.08
    gie
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    falls
    -0.07
    ä¼ĹæīĢåij¨çŁ¥
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    spawn
    -0.07
    chi
    -0.07
    POSITIVE LOGITS
    Ø©
    0.09
    quam
    0.08
    æĢ§çļĦ
    0.08
    à¦Ńাবà§ĩ
    0.07
    èī²åĪĹ
    0.07
    ÅĤek
    0.07
    е
    0.07
    ëį¤
    0.07
    à¹Ĩ
    0.07
    à¦ĩ
    0.07
    Activations Density 0.019%

    No Known Activations