© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63789
    Prev
    Next
    INDEX
    Explanations

    closed or collapsed

    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
    æ¸Ľ
    -0.08
    .removeChild
    -0.08
    åĩıéĢŁ
    -0.08
     diminu
    -0.07
    omic
    -0.07
    ç»ı常æĢ§
    -0.07
    åĩı
    -0.07
    缩çŁŃäºĨ
    -0.07
    æľ¬èģĮ
    -0.07
    annes
    -0.07
    POSITIVE LOGITS
     virgin
    0.09
    æĪĸæľª
    0.09
    空çļĦ
    0.09
    åķĵ
    0.09
    çĬ¶æĢģçļĦ
    0.08
    ä»Ģä¹Īéĥ½æ²¡æľī
    0.08
    çĬ¶æĢģ
    0.08
     Abs
    0.08
    çĬ¶æĢģä¸ĭ
    0.08
    è¿İæİ¥
    0.08
    Activations Density 0.167%

    No Known Activations