© 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. 64277
    Prev
    Next
    INDEX
    Explanations

    completeness or absence

    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
    imon
    -0.07
    otto
    -0.07
    æľīæĿ¡ä»¶
    -0.07
    æķħèĢĮ
    -0.07
    æĦıåij³
    -0.06
    ç§įç§į
    -0.06
    Rather
    -0.06
    iq
    -0.06
    ser
    -0.06
    鹤
    -0.06
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.10
    éģĹæ¼ı
    0.09
    涵çĽĸ
    0.09
    涵çĽĸäºĨ
    0.09
    ä¸įæ¼ı
    0.09
    æĥ³åĪ°çļĦ
    0.09
    åºĶåĮħæĭ¬
    0.08
    à¸Ħรà¸ļ
    0.08
    éĩį大éģĹæ¼ı
    0.08
    éĩįè¦ģçļĦ
    0.08
    Activations Density 0.015%

    No Known Activations