© 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. 38095
    Prev
    Next
    INDEX
    Explanations

    die or dice

    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
    issime
    -0.08
    akte
    -0.07
    laÅŁ
    -0.07
    ations
    -0.07
    emps
    -0.07
    æľŁåĨħ
    -0.07
    poons
    -0.07
    dated
    -0.07
    å¤ļãģĦ
    -0.07
    гоÑĢиÑĤ
    -0.07
    POSITIVE LOGITS
    lectric
    0.11
    ़
    0.10
    erman
    0.08
    endom
    0.08
    ement
    0.08
    es
    0.08
    ãģªãĤīãģļ
    0.07
    ÑĶÑİ
    0.07
    olo
    0.07
    eware
    0.07
    Activations Density 0.010%

    No Known Activations