© 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. 59752
    Prev
    Next
    INDEX
    Explanations

    magnitude, size, or quantities

    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
    è¾ĥéĩį
    -0.10
    è¾ĥå¼±
    -0.09
    è¾ĥ强çļĦ
    -0.09
     pricey
    -0.09
    arris
    -0.09
    ä¸į大çļĦ
    -0.09
    æĹĹ
    -0.09
    åĽłæĤ¨çļĦ
    -0.08
    尤为éĩįè¦ģ
    -0.08
    è¾ĥ大
    -0.08
    POSITIVE LOGITS
     unimagin
    0.09
     billions
    0.09
     astronom
    0.09
    æŀģåħ¶
    0.08
     even
    0.08
    éģ¥è¿ľçļĦ
    0.08
     tiny
    0.08
     extremely
    0.07
    åĬ¨åĬ¨
    0.07
     thousands
    0.07
    Activations Density 0.030%

    No Known Activations