© 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. 8400
    Prev
    Next
    INDEX
    Explanations

    diseased or damaged parts

    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
    åı£æ°´
    -0.07
    å¦Ĥæ°´
    -0.07
    åŁºç¡ĢæĢ§
    -0.07
    ablement
    -0.07
    adle
    -0.07
    anski
    -0.06
     bases
    -0.06
    åı£å¸Ĥ
    -0.06
    ismatic
    -0.06
    anzi
    -0.06
    POSITIVE LOGITS
    ridden
    0.09
    äºĨçļĦ
    0.09
    累累
    0.08
    liest
    0.08
    ä¸įåłª
    0.08
    /problem
    0.08
    ÛķÚ©
    0.08
    æīĢåľ¨çļĦ
    0.07
    طر
    0.07
    è¿ĩçļĦ
    0.07
    Activations Density 0.156%

    No Known Activations