© 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. 35046
    Prev
    Next
    INDEX
    Explanations

    mean or key

    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
    æIJĤ
    -0.07
    éģĹ
    -0.06
    lassen
    -0.06
    mane
    -0.06
     tid
    -0.06
    OGO
    -0.06
    лÑıм
    -0.06
    ï¸İ
    -0.06
    Cheers
    -0.06
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.06
    POSITIVE LOGITS
    vector
    0.13
    åIJijéĩı
    0.13
     vector
    0.13
    çŁ¢éĩı
    0.13
     vectors
    0.12
     Vector
    0.11
    Vector
    0.11
    _VECTOR
    0.11
     vect
    0.10
    _vector
    0.10
    Activations Density 0.074%

    No Known Activations