© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59953
    Prev
    Next
    INDEX
    Explanations

    strengths, limitations, conditions, redistributions, universal, system

    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
    Negative Logits
    ÙĬØ´
    -0.07
    ault
    -0.07
    ä¸įçĦ¶
    -0.06
    ë¡ľ
    -0.06
    èĬĴ
    -0.06
    ponse
    -0.06
    ateral
    -0.06
    auce
    -0.06
    ect
    -0.06
    è¦ģæĺ¯
    -0.06
    POSITIVE LOGITS
    iging
    0.09
    ycz
    0.08
    ä¸ī两
    0.08
     ######
    0.08
     #####
    0.08
    飦
    0.08
    иÑģÑĮ
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    oger
    0.07
    åŁł
    0.07
    Activations Density 0.013%

    No Known Activations