© 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. 10403
    Prev
    Next
    INDEX
    Explanations

    see, sight, hear, smell

    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
     silent
    -0.07
    å½Ĵäºİ
    -0.07
    unction
    -0.07
     proven
    -0.06
    æĴĴ
    -0.06
     tested
    -0.06
    atte
    -0.06
    æ²īå¯Ĥ
    -0.06
    æŁ¥
    -0.06
    åŀĭ人æīį
    -0.06
    POSITIVE LOGITS
    æ¸ħæĻ°
    0.13
    æ¸ħæĻ°çļĦ
    0.13
     visible
    0.12
    -visible
    0.11
     visibility
    0.11
    visible
    0.11
    åı¯è§ģ
    0.11
    à¸Ĭัà¸Ķ
    0.11
    è½®å»ĵ
    0.10
    ä¾Ŀç¨Ģ
    0.10
    Activations Density 0.165%

    No Known Activations