© 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. 25133
    Prev
    Next
    INDEX
    Explanations

    :C, L, :B, >S, .D, SFML

    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
    oubl
    -0.07
    ifold
    -0.06
    ä¼ı
    -0.06
    olute
    -0.06
    ataset
    -0.06
    irection
    -0.06
    enerate
    -0.06
    inned
    -0.06
    ansion
    -0.06
    allenge
    -0.06
    POSITIVE LOGITS
    er
    0.09
    jenigen
    0.09
    eram
    0.08
    ulam
    0.08
    eri
    0.08
     Ilmais
    0.08
    eret
    0.07
    Äįem
    0.07
    nega
    0.07
    eres
    0.07
    Activations Density 1.057%

    No Known Activations