© 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. 24253
    Prev
    Next
    INDEX
    Explanations

    wrong context or usage

    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
    elv
    -0.08
    å°½åı¯èĥ½
    -0.07
    ä¸įäºĨçļĦ
    -0.07
    å¸ĮæľĽåľ¨
    -0.07
    akh
    -0.07
    elok
    -0.07
    æīĢæľª
    -0.07
    imeo
    -0.07
    ilÃł
    -0.07
    Ä«m
    -0.07
    POSITIVE LOGITS
    è¿ĺæĬĬ
    0.08
    ä¸Ĭæ·»
    0.08
    venu
    0.08
    chal
    0.08
    llen
    0.07
    请çĻ»å½ķ
    0.07
    ä¸įè¦ģæĬĬ
    0.07
    åĿļæĮģæĬĬ
    0.07
    请åijĬçŁ¥
    0.07
    /DD
    0.07
    Activations Density 0.043%

    No Known Activations