© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17757
    Prev
    Next
    INDEX
    Explanations

    as above, as before, as usual

    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
    isque
    -0.07
    Âł
    -0.07
    te
    -0.06
    åħ¶æīĢ
    -0.06
    odar
    -0.06
    ä¸İåħ¶
    -0.06
    ième
    -0.06
    æľĭ
    -0.06
    åħ¶
    -0.06
    åı¯è¨Ģ
    -0.06
    POSITIVE LOGITS
    viel
    0.09
    ÙĬÙĨت
    0.09
    èĭ±æĸĩåIJįåŃĹ
    0.08
    æĻºèĥ½ç§ijæĬĢæľīéĻIJåħ¬åı¸
    0.08
    ãĤĵãģ³
    0.08
    dirs
    0.08
    elit
    0.08
    uva
    0.08
    ÅĦczy
    0.08
    æĥ³æĸ¹
    0.08
    Activations Density 0.005%

    No Known Activations