© 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. 34974
    Prev
    Next
    INDEX
    Explanations

    category names and identifiers

    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
    o
    -0.07
    ¹Ħ
    -0.07
    داÙħ
    -0.07
    ĸ
    -0.06
    ¹
    -0.06
    è§ģçļĦ
    -0.06
    iad
    -0.06
    ScrollIndicator
    -0.06
    çłĮ
    -0.06
    çī¹æľĹ
    -0.06
    POSITIVE LOGITS
    ле
    0.07
    rogram
    0.07
    åįĹå±±
    0.07
    æ°Ľ
    0.07
    è¿ĺæľīå¾ħ
    0.06
    lui
    0.06
    lij
    0.06
    éªı
    0.06
    ë£Į
    0.06
    yme
    0.06
    Activations Density 0.002%

    No Known Activations