© 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. 9560
    Prev
    Next
    INDEX
    Explanations

    commas separating names or citations

    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
    ful
    -0.07
    为天
    -0.07
     воÑĤ
    -0.07
    ק×Ķ
    -0.07
    åIJİæĦŁ
    -0.07
    agi
    -0.07
    lessness
    -0.07
    ENZ
    -0.07
    os
    -0.06
    ÑĮÑı
    -0.06
    POSITIVE LOGITS
    rawer
    0.07
    µ
    0.06
    (strict
    0.06
    /proto
    0.06
    usher
    0.06
    åı¯æ¢¦
    0.06
    manos
    0.06
    phans
    0.06
    ä¸Ģä½ľ
    0.06
    ytes
    0.06
    Activations Density 0.018%

    No Known Activations