© 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. 62311
    Prev
    Next
    INDEX
    Explanations

    numbers ending in .1

    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
    n
    -0.13
    t
    -0.11
    ,
    -0.10
    i
    -0.10
    (
    -0.09
    -
    -0.09
    m
    -0.09
    en
    -0.09
    '
    -0.09
    [
    -0.09
    POSITIVE LOGITS
    <|box_end|>
    0.14
    plevel
    0.11
    istics
    0.10
    ffset
    0.10
    ìį¨
    0.10
    phans
    0.10
    istic
    0.10
    ksen
    0.10
    bject
    0.10
    ÅĽÄĩ
    0.10
    Activations Density 0.269%

    No Known Activations