© 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. 23226
    Prev
    Next
    INDEX
    Explanations

    Australian Signals Directorate

    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
    enio
    -0.08
    inov
    -0.08
    érito
    -0.08
    aian
    -0.08
    ganti
    -0.08
    <tool_response>
    -0.08
    ughs
    -0.07
    erii
    -0.07
    yono
    -0.07
    adini
    -0.07
    POSITIVE LOGITS
    adays
    0.09
    gether
    0.08
    minster
    0.08
    ful
    0.07
    sburgh
    0.07
    orca
    0.06
    bsites
    0.06
    odore
    0.06
    %C
    0.06
    gerald
    0.06
    Activations Density 2.136%

    No Known Activations