© 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. 26727
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    ayang
    -0.07
    dana
    -0.07
    edio
    -0.07
    è¿Ļä¹Īå¤ļ
    -0.06
    ,
    -0.06
    é½IJé½IJ
    -0.06
    ewn
    -0.06
    ä»įæľª
    -0.06
     Academic
    -0.06
    edel
    -0.06
    POSITIVE LOGITS
    身临åħ¶å¢ĥ
    0.12
     etc
    0.11
    åĭĩå¾Ģ缴åīį
    0.10
     коÑĤоÑĢого
    0.10
    两åѦä¸Ģåģļ
    0.10
    ä¸įåı¯æĢĿè®®
    0.10
    äºĭåįĬåĬŁåĢį
    0.10
    etc
    0.09
    çĶļèĩ³æĺ¯
    0.09
    ä¿¡æģ¯çŃī
    0.09
    Activations Density 0.354%

    No Known Activations