© 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. 13483
    Prev
    Next
    INDEX
    Explanations

    lists with punctuation or "responses"

    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
     Sond
    -0.08
    æĺŃ
    -0.07
    为äºĨä¿ĿæĬ¤
    -0.07
    ãĥĭãĤ¢
    -0.07
    ç¥IJ
    -0.07
    .OrderBy
    -0.07
     indict
    -0.07
    æĭĹ
    -0.06
    çĹħç¨ĭ
    -0.06
    ìŀ¬ëĭ¨
    -0.06
    POSITIVE LOGITS
    ipan
    0.07
    LTR
    0.07
    ITT
    0.07
    ãģ¤ãĤĤ
    0.07
    ä¹ŁæľīæīĢ
    0.07
    าศ
    0.07
    èĢĮ为
    0.06
    åŃĿæķ¬
    0.06
    失
    0.06
    зÑĭ
    0.06
    Activations Density 0.010%

    No Known Activations