© 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. 25547
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
    коÑĤ
    -0.07
    achu
    -0.07
    оÑĤа
    -0.07
    ograph
    -0.06
    åĿĬ
    -0.06
    firma
    -0.06
    à¸Ĺาà¸Ļ
    -0.06
    åı¦ä¸Ģæĸ¹
    -0.06
    å°Ķ
    -0.06
    cia
    -0.06
    POSITIVE LOGITS
    wassen
    0.07
    enius
    0.07
    æľī两ç§į
    0.07
    å¼ĢæĿ¥
    0.07
    ért
    0.07
    çļĦæĦıæĢĿæĺ¯
    0.06
    TokenType
    0.06
    éģºçĶ£
    0.06
    akar
    0.06
    è®°åĪĨ
    0.06
    Activations Density 0.001%

    No Known Activations