© 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. 45834
    Prev
    Next
    INDEX
    Explanations

    scale values (1x, 2x, 3x)

    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
     europé
    -0.08
    åıĬæľīåħ³
    -0.07
    lsa
    -0.07
    ULE
    -0.07
    ï¸ı
    -0.07
    лÑıÑĤ
    -0.07
    ein
    -0.07
    elman
    -0.07
    ине
    -0.07
    tto
    -0.07
    POSITIVE LOGITS
    è·ĭ
    0.07
    篤
    0.06
    STDOUT
    0.06
     Tradition
    0.06
     Disabled
    0.06
    ä¸įæĸŃ丰å¯Į
    0.06
    uy
    0.06
    ç¬ĥ
    0.06
    conomics
    0.06
    åĮĿ
    0.06
    Activations Density 0.007%

    No Known Activations