© 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. 38872
    Prev
    Next
    INDEX
    Explanations

    problems or errors

    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
    allah
    -0.08
    æīįçŁ¥éģĵ
    -0.07
    天å¿ĥ
    -0.07
    ero
    -0.07
    ä¸įåĩ¡
    -0.06
     Shields
    -0.06
    æĥħç¼ĺ
    -0.06
    rie
    -0.06
    æľīæŶåĢĻ
    -0.06
    Forget
    -0.06
    POSITIVE LOGITS
     whatsoever
    0.10
    彬彬
    0.07
    æĹłä¸į
    0.07
    orius
    0.07
     aparent
    0.07
    Checked
    0.07
    -checked
    0.07
    éĢĤé¾Ħ
    0.07
    checked
    0.07
     lurking
    0.07
    Activations Density 0.052%

    No Known Activations