© 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. 60059
    Prev
    Next
    INDEX
    Explanations

    statistical tests chi-square correspondence kappa

    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
    ä¸įè¿ĺ
    -0.07
    æĹ¥æĸ°æľĪå¼Ĥ
    -0.07
    rog
    -0.07
    çĶŁæĢķ
    -0.07
    .setdefault
    -0.07
    æ±Ĥè´Ńä¿¡æģ¯
    -0.07
    é«ĺ级工ç¨ĭå¸Ī
    -0.07
    uber
    -0.07
    æħ¢
    -0.07
    åĪ©çİĩ
    -0.07
    POSITIVE LOGITS
     categorical
    0.10
    EventData
    0.09
    earn
    0.08
    enius
    0.08
    wald
    0.08
    counts
    0.07
    éĺ´éĺ³
    0.07
    ivot
    0.07
    fert
    0.07
    obbies
    0.07
    Activations Density 0.025%

    No Known Activations