© 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. 44795
    Prev
    Next
    INDEX
    Explanations

    specific details

    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
    ppure
    -0.09
    缸è¾ħ缸æĪIJ
    -0.09
    åĬłæĭ¿å¤§
    -0.09
    æ¯ıä¸Ģ件
    -0.08
    imately
    -0.08
    åIJĦ项è§Ħç«łåĪ¶åº¦
    -0.08
    itles
    -0.08
    isar
    -0.08
    æ°´åĻ¨
    -0.08
    ardon
    -0.08
    POSITIVE LOGITS
    enom
    0.07
    ÙĦاÙĤ
    0.07
    åIJ¾
    0.06
    æĹ
    0.06
    at
    0.06
    /
    0.06
     McGu
    0.06
    å§Ķ
    0.06
    rott
    0.05
    æĪĸå¤ļ个
    0.05
    Activations Density 1.024%

    No Known Activations