© 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. 13047
    Prev
    Next
    INDEX
    Explanations

    seasonal, regional, developmental variations

    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
    hets
    -0.09
    çīµ
    -0.08
    elda
    -0.08
    геÑĢ
    -0.07
    _IRQ
    -0.07
    æĸĩ件æĪĸ
    -0.07
    ukur
    -0.07
    êmio
    -0.07
    FromClass
    -0.07
    -facing
    -0.07
    POSITIVE LOGITS
     differences
    0.11
    ë³Ħ
    0.11
    éĹ´çļĦ
    0.09
    éĹ´
    0.09
    -specific
    0.08
    -wise
    0.08
    å·®å¼Ĥ
    0.08
    ë³Ħë¡ľ
    0.08
     difference
    0.08
    侧éĩį
    0.08
    Activations Density 0.089%

    No Known Activations