© 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. 44856
    Prev
    Next
    INDEX
    Explanations

    None

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tir
    -0.07
    ulton
    -0.07
    éĢĢ
    -0.07
    θÎŃ
    -0.07
    ts
    -0.06
    weg
    -0.06
    ä¸įä¿¡
    -0.06
    ump
    -0.06
    cg
    -0.06
     loc
    -0.06
    POSITIVE LOGITS
     neither
    0.11
    ä¸įåŃĺåľ¨
    0.11
     none
    0.11
    æļĤæĹł
    0.11
    _None
    0.10
     nothing
    0.10
     None
    0.10
     ningún
    0.10
    .None
    0.10
    none
    0.10
    Activations Density 0.171%

    No Known Activations