© 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. 8452
    Prev
    Next
    INDEX
    Explanations

    petition, claimant, impact

    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
    ç§ijæĬĢåѦéĻ¢
    -0.07
    laÅŁ
    -0.07
    管çIJĨæīĢ
    -0.07
    طة
    -0.07
    ided
    -0.07
     Pussy
    -0.07
    INATION
    -0.07
    жноÑģÑĤÑĮ
    -0.06
    lilik
    -0.06
    Ùĭ
    -0.06
    POSITIVE LOGITS
    èĢħ
    0.20
    èĢħåĴĮ
    0.20
    ers
    0.18
    èĢħä¸İ
    0.18
    èĢħçļĦ
    0.17
    èĢħåľ¨
    0.16
    èĢħåı¯
    0.15
    èĢħãģ®
    0.15
    åijĺ
    0.15
    èĢħ为
    0.15
    Activations Density 0.982%

    No Known Activations