© 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. 26731
    Prev
    Next
    INDEX
    Explanations

    figure and caption references

    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
    å·
    -0.07
    éħ¸
    -0.07
    æķ´
    -0.06
    åįģæĿ¡
    -0.06
    /linux
    -0.06
    åģ¥
    -0.06
    ¨
    -0.06
     suspended
    -0.06
    ¼
    -0.06
     бÑĢе
    -0.06
    POSITIVE LOGITS
    -caption
    0.09
    æľīæīĢæĢĿ
    0.08
    arness
    0.08
    _inline
    0.08
    å§Ĭ
    0.08
    áĥ£áĥł
    0.08
    figure
    0.08
    upp
    0.07
    çĪ·
    0.07
    æīĢ示
    0.07
    Activations Density 0.014%

    No Known Activations