© 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. 37529
    Prev
    Next
    INDEX
    Explanations

    all of it land or all zeros

    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
    诸å¤ļ
    -0.09
    æķ´ä¸ªäºº
    -0.09
    许å¤ļ
    -0.08
    许å¤ļçļĦ
    -0.08
    Backdrop
    -0.08
    ä¸ĩä¸Ī
    -0.08
    kens
    -0.08
    istan
    -0.08
     лÑİбой
    -0.08
    許å¤ļ
    -0.08
    POSITIVE LOGITS
    æĪĸéĥ¨åĪĨ
    0.16
     تÙĤرÙĬب
    0.13
     except
    0.12
    owing
    0.10
    igator
    0.10
    except
    0.10
    Except
    0.09
    usions
    0.09
     Except
    0.08
    ä¹Łéĥ½æĺ¯
    0.08
    Activations Density 0.075%

    No Known Activations