© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39130
    Prev
    Next
    INDEX
    Explanations

    !important or !default

    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
    ishes
    -0.09
    an
    -0.08
    lear
    -0.07
    aning
    -0.07
    reta
    -0.07
    rees
    -0.07
     زاÙĦت
    -0.07
    áŀ¶áŀĵ
    -0.07
    avor
    -0.06
    _configure
    -0.06
    POSITIVE LOGITS
    omp
    0.07
    .ng
    0.07
    ä¸įåĪ°çļĦ
    0.07
    åļı
    0.07
    ļ
    0.07
    apa
    0.07
    adius
    0.07
    Ïīμα
    0.06
    жим
    0.06
    ä¸įå±Ī
    0.06
    Activations Density 0.001%

    No Known Activations