© 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. 44535
    Prev
    Next
    INDEX
    Explanations

    referred to as

    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
    å¦Ĥæ¶īåıĬ
    -0.08
    ãģ£ãģįãĤĬ
    -0.08
    æ¶ī
    -0.07
    ä»»åĬ³
    -0.07
    chein
    -0.07
    é§
    -0.07
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ¯
    -0.07
    bens
    -0.07
     whatsoever
    -0.07
    pig
    -0.07
    POSITIVE LOGITS
    ä¹Łåı«
    0.10
     appunto
    0.09
     [].
    0.09
    ä¹Łç§°
    0.08
    è£ĺ
    0.07
    ä¹Łç§°ä¸º
    0.07
    ãģ¨åij¼ãģ°
    0.07
    åħ¶çī¹å¾ģ
    0.07
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.07
    sieme
    0.06
    Activations Density 0.246%

    No Known Activations