© 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. 3809
    Prev
    Next
    INDEX
    Explanations

    low values or thresholds

    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
    оÑģÑģ
    -0.08
    receipt
    -0.08
    ä¸įèµ·æĿ¥
    -0.07
    æĢ§å¼º
    -0.07
    åıªä¸įè¿ĩ
    -0.07
    wend
    -0.07
    缺ä¸Ģä¸įåı¯
    -0.07
    iliano
    -0.07
    acific
    -0.07
    ä¸įéĹ´æĸŃ
    -0.07
    POSITIVE LOGITS
     (<
    0.13
    (<
    0.10
     [<
    0.09
     drast
    0.09
    å¦Ĥæ°´
    0.09
     (\<
    0.08
    allee
    0.07
     kuin
    0.07
    æľī为
    0.07
    ä¸įä¸ĭæĿ¥
    0.07
    Activations Density 0.187%

    No Known Activations