© 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. 58666
    Prev
    Next
    INDEX
    Explanations

    xml structure with č

    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
    assi
    -0.07
    éĤ¯éĥ¸å¸Ĥ
    -0.07
    çļĦä¸Ģå®ļ
    -0.07
    anga
    -0.07
    æĹ¥ä¸Ĭ
    -0.07
    åıĤè®Ń
    -0.07
    iegel
    -0.07
    Legend
    -0.07
    éħįçļĦ
    -0.07
    Ñijм
    -0.07
    POSITIVE LOGITS
    inherit
    0.08
    inage
    0.06
    è¶ħå¤ļ
    0.06
     Fundamental
    0.06
    ãĥij
    0.06
    plex
    0.06
     inheritance
    0.06
    betal
    0.06
    宫
    0.06
     fundamental
    0.06
    Activations Density 0.091%

    No Known Activations