© 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. 16375
    Prev
    Next
    INDEX
    Explanations

    inside

    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
    sWith
    -0.12
    ìį¨
    -0.12
    zelf
    -0.11
    spur
    -0.10
    ÙİÙijÙĩÙı
    -0.10
    виÑĨа
    -0.10
    åĩºèĩªå·±çļĦ
    -0.10
    écr
    -0.10
    stvÃŃ
    -0.09
    stalk
    -0.09
    POSITIVE LOGITS
    /out
    0.12
    e
    0.08
    a
    0.08
    Ùĭ
    0.07
    а
    0.07
    hood
    0.07
    /on
    0.07
    ener
    0.07
    halb
    0.07
    è¯ĿæĿ¥
    0.06
    Activations Density 0.035%

    No Known Activations