© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11764
    Prev
    Next
    INDEX
    Explanations

    saturation and contrast

    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
    ichert
    -0.07
    ×Ĵ×Ļ
    -0.07
    foot
    -0.06
    ichi
    -0.06
     Speedway
    -0.06
    ë²Ĺ
    -0.06
    ä¸Ģåıij
    -0.06
    æ»¨æ±Ł
    -0.06
    æĪĺçķ¥å¸ĥå±Ģ
    -0.06
    èĦļ
    -0.06
    POSITIVE LOGITS
    强度
    0.11
     intensity
    0.10
     strength
    0.09
    強度
    0.09
    强度çļĦ
    0.09
     strongest
    0.08
     amplitude
    0.08
    ä¸įåĢĴ
    0.08
    ç¨ĭ度
    0.08
    Intensity
    0.08
    Activations Density 0.009%

    No Known Activations