© 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. 29595
    Prev
    Next
    INDEX
    Explanations

    programming language configuration

    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
    åĪĨå¤ĸ
    -0.08
    çļĦ大éĩı
    -0.08
    ogle
    -0.08
    føl
    -0.07
    lach
    -0.07
    föl
    -0.07
    ouve
    -0.07
    ytt
    -0.07
    hton
    -0.07
    æīįåŃIJ
    -0.07
    POSITIVE LOGITS
    ä¸įåı¯æĢĿè®®
    0.09
    åĭĩå¾Ģ缴åīį
    0.09
    身临åħ¶å¢ĥ
    0.08
    以åıĬ
    0.08
    åħ¢åħ¢ä¸ļä¸ļ
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
     etc
    0.07
    俱ä¹IJéĥ¨
    0.07
    æĸ°åĬłåĿ¡
    0.07
    Activations Density 0.097%

    No Known Activations