© 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. 62371
    Prev
    Next
    INDEX
    Explanations

    `[]`, `{}`, `()`

    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
     NOTICE
    -0.08
    éĥijéĩį声æĺİ
    -0.08
    aight
    -0.07
    ä¹³æ±ģ
    -0.07
    ิà¹Īà¸ĩ
    -0.07
    -script
    -0.07
    eim
    -0.07
    é½IJå¿ĥ
    -0.07
    åį´ä¸įèĥ½
    -0.07
    otty
    -0.07
    POSITIVE LOGITS
    ä¹Łæ²¡æľī
    0.12
     nor
    0.09
    ä¹Łæ²Ĵæľī
    0.08
    ä½Ĩæľī
    0.08
     neither
    0.08
     tampoco
    0.08
    ipun
    0.08
    ä»»ä½ķ人
    0.08
    æĽ´æ²¡æľī
    0.08
    ä¹Łä¸įåı¯èĥ½
    0.07
    Activations Density 0.094%

    No Known Activations