© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44839
    Prev
    Next
    INDEX
    Explanations

    container parts or examples

    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
    omagnet
    -0.07
    occa
    -0.07
    ä¸ĢçĽ´ä»¥
    -0.06
    ire
    -0.06
    enaar
    -0.06
    å¿ĥæĥħ
    -0.06
    ĵĺ
    -0.06
    oppi
    -0.06
    åĨįä¸ī
    -0.06
    æĸ°åŀĭåĨłçĬ¶çĹħæ¯ĴæĦŁæŁĵçļĦ
    -0.06
    POSITIVE LOGITS
    ç«Łæĺ¯
    0.08
    尼奥
    0.08
    éķij
    0.07
    umbs
    0.07
    ujung
    0.07
    è¿Ļæł·åı¯ä»¥
    0.07
    å°±åı«
    0.07
    æĹ¶ä½¿çĶ¨
    0.07
    èIJ½èĬ±
    0.07
    å¤ļè¾¾
    0.07
    Activations Density 0.038%

    No Known Activations