© 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. 56073
    Prev
    Next
    INDEX
    Explanations

    trace

    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
    strand
    -0.08
    ield
    -0.08
    ropri
    -0.08
    elsey
    -0.07
    recision
    -0.07
    -fashioned
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    ropa
    -0.07
    enerate
    -0.07
    ë¦Ħ
    -0.07
    POSITIVE LOGITS
    eves
    0.10
    åı¯å¾ª
    0.09
    gehend
    0.09
    orial
    0.09
    althy
    0.08
    ä¸ĭæĿ¥çļĦ
    0.08
    uely
    0.08
    Ùĩ
    0.08
    踪
    0.07
    ÑĥÑİÑī
    0.07
    Activations Density 0.045%

    No Known Activations