© 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. 4215
    Prev
    Next
    INDEX
    Explanations

    tag archives

    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
    Äįen
    -0.08
    åħ¸åŀĭ
    -0.07
    æĿ¡æĿ¡
    -0.07
    ãģ«ãģı
    -0.07
    æĭł
    -0.06
    rf
    -0.06
    è¦ģèµ°
    -0.06
     Foo
    -0.06
    ä¸ĭ称
    -0.06
    äºĶåħŃ
    -0.06
    POSITIVE LOGITS
    egade
    0.08
    éĽĨåĽ¢èĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.07
    ìĻķ
    0.07
    æİī
    0.07
    ottle
    0.07
    éģĵçIJĨ
    0.07
    [:,:,
    0.06
    /slick
    0.06
    æ¦ľ
    0.06
    ugins
    0.06
    Activations Density 0.002%

    No Known Activations