© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57096
    Prev
    Next
    INDEX
    Explanations

    code generated by the command above;

    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
     fle
    -0.06
    os
    -0.06
    åĽłç´łå½±åĵį
    -0.06
    룩
    -0.06
    ä¸ĸ
    -0.06
    pars
    -0.06
    åįĩ
    -0.06
    -os
    -0.06
    ç»ĻåĪ«äºº
    -0.06
    èĢĮå·²
    -0.06
    POSITIVE LOGITS
    :view
    0.09
    Subview
    0.08
    cco
    0.08
    enco
    0.08
    iors
    0.07
    cca
    0.07
    á»ijt
    0.07
    mand
    0.07
    anch
    0.07
    OrFail
    0.07
    Activations Density 0.002%

    No Known Activations