© 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. 10264
    Prev
    Next
    INDEX
    Explanations

    you

    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
    æĺ¯
    -0.10
    åĭĩå¾Ģ缴åīį
    -0.10
    åĴĮ
    -0.09
    äºĭåįĬåĬŁåĢį
    -0.09
    ible
    -0.09
    ä¸įåı¯æĢĿè®®
    -0.09
    åľ¨
    -0.09
    åľ¨å¿ĥéĩĮ
    -0.08
    ãģ®
    -0.08
    身临åħ¶å¢ĥ
    -0.08
    POSITIVE LOGITS
    -même
    0.12
    /her
    0.12
    zelf
    0.10
    çļĦ人çĶŁ
    0.10
    çļĦ人éĻħ
    0.10
    çļĦä¸ĢåĪĩ
    0.10
    inerary
    0.10
    ä¿©
    0.10
    çļĦä¸ĢåĪĩéĥ½
    0.10
    çļĦ人éĻħåħ³ç³»
    0.10
    Activations Density 0.006%

    No Known Activations