© 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. 10275
    Prev
    Next
    INDEX
    Explanations

    The value or type of parameter

    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
    retti
    -0.08
    ISTI
    -0.08
    èį¯çļĦ
    -0.08
    ä½ľåĪĻ
    -0.07
     acom
    -0.07
    retto
    -0.07
    gom
    -0.07
     theirs
    -0.07
    retta
    -0.07
    Į
    -0.07
    POSITIVE LOGITS
    ç¥
    0.07
    Ùijا
    0.06
    æĵį
    0.06
    è¡ĵ
    0.06
    ä¸Ģèµ·åŃ¦ä¹ł
    0.06
    èijī
    0.06
    hev
    0.06
    宿
    0.06
    æĥ³äºĨè§£æĽ´å¤ļ
    0.06
    antas
    0.06
    Activations Density 0.007%

    No Known Activations