© 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. 32929
    Prev
    Next
    INDEX
    Explanations

    left and right sides

    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
    æŃ£ç¡®çŃĶæ¡Ī
    -0.07
    lund
    -0.07
    jang
    -0.07
    Ú©Ø´
    -0.07
    è¿Ļç§įçݰ象
    -0.07
    æµĭè¯ķç»ĵæŀľ
    -0.06
    asen
    -0.06
    äºĨä¸ĢåĪĩ
    -0.06
    راÙĨ
    -0.06
    -0.06
    POSITIVE LOGITS
    trop
    0.08
    åIJįåı«
    0.08
    æ¶īåıĬåĪ°
    0.08
    (er
    0.07
    åĬ¨åĬĽæĸ¹éĿ¢
    0.07
    ¯¯¯¯
    0.07
    é¦ĸåħĪéľĢè¦ģ
    0.07
    tis
    0.07
     term
    0.07
    vene
    0.07
    Activations Density 0.002%

    No Known Activations