© 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. 51153
    Prev
    Next
    INDEX
    Explanations

    also investigate

    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
     instead
    -0.08
     accordingly
    -0.08
     indeed
    -0.07
    ä¹Łç¡®å®ŀ
    -0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.07
     never
    -0.07
    çļĦä¸įåIJĮ
    -0.07
    ä¹Łå¥½
    -0.07
    ä¸įåIJĮçļĦ人
    -0.07
     ëĮĢìĭł
    -0.07
    POSITIVE LOGITS
    人è¦ģ
    0.09
    åħ¶å®ĥçļĦ
    0.09
    åı¦å¤ĸä¸Ģ个
    0.08
    hausen
    0.08
    èĢĥèĻij
    0.08
    trup
    0.08
    åĽłç´łå½±åĵį
    0.08
    æĪĸéĥ¨åĪĨ
    0.08
    è¦ģèĢĥèĻij
    0.08
    ảnh
    0.07
    Activations Density 0.051%

    No Known Activations