© 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. 32493
    Prev
    Next
    INDEX
    Explanations

    names ending in et.l or ley

    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
    ç»ıå¾Ĺèµ·
    -0.08
    交大
    -0.07
    amente
    -0.07
     piazz
    -0.07
     напÑĢа
    -0.06
    à¸ŀาà¸ģ
    -0.06
    çıĪ
    -0.06
    åĵªå¤©
    -0.06
    该èĤ¡
    -0.06
    è¡Ŀ
    -0.06
    POSITIVE LOGITS
    ãĢĬ
    0.11
    æĴ°
    0.10
    åľ¨ä»ĸçļĦ
    0.09
    ç¬Ķä¸ĭçļĦ
    0.08
    åľ¨åħ¶
    0.08
     ãĢĬ
    0.08
    äºĭä¸ļåįķä½įæĭĽèģĺ
    0.08
    大æĭĽ
    0.08
    rl
    0.08
    ä¸Ģåį·
    0.07
    Activations Density 0.021%

    No Known Activations