© 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. 48055
    Prev
    Next
    INDEX
    Explanations

    cleavage of

    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
    åį³åı¯æŁ¥çľĭ
    -0.07
    ä¸ĭ载使çĶ¨
    -0.07
    为äºĨèĥ½
    -0.07
    çĶ¨å¾®ä¿¡
    -0.07
     appro
    -0.07
    åľ¨å»ºè®¾
    -0.07
    æĪĸ使çĶ¨
    -0.06
    amba
    -0.06
    æīįèĥ½æĽ´å¥½åľ°
    -0.06
    borg
    -0.06
    POSITIVE LOGITS
    ä¸įçķĻ
    0.09
     converting
    0.09
    ä¸įåģľ
    0.09
    èĦ±
    0.09
    转为
    0.08
    ä¸ĢæĿ¡é¾Ļ
    0.08
     conversion
    0.08
    ä¸ĢæŃ¥
    0.08
    两æŃ¥
    0.08
     convert
    0.08
    Activations Density 0.011%

    No Known Activations