© 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. 59073
    Prev
    Next
    INDEX
    Explanations

    |-wave, -patch, apocrine, apatite, ELF

    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
    è¿Ļæł·å°±åı¯ä»¥
    -0.08
    scss
    -0.07
    åĴĮæ³ķå¾ĭ
    -0.07
    æ¯ķ
    -0.07
    zonder
    -0.07
    æĥ³æ³ķ
    -0.06
    åĪĨéĩİ
    -0.06
    åľ¨ç»ıæµİ
    -0.06
    åľ¨æ³ķå¾ĭ
    -0.06
    å¥¢æľĽ
    -0.06
    POSITIVE LOGITS
    为主çļĦ
    0.08
     imper
    0.08
     Default
    0.07
    å±ħå¤ļ
    0.07
    å·¥ä½ľå®ŀéĻħ
    0.07
    为主
    0.07
    agged
    0.07
    æĺ¯çĽ®åīį
    0.07
    çī¹æľī
    0.07
    _TYP
    0.07
    Activations Density 0.086%

    No Known Activations