© 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. 27694
    Prev
    Next
    INDEX
    Explanations

    comparisons and operators

    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
     lắm
    -0.08
    ctr
    -0.07
    gt
    -0.07
    ETTE
    -0.07
    ä¹ĭåīij
    -0.07
    ä¸ĢèĪ¬ä¸º
    -0.07
    bia
    -0.06
    ä¸ĢèĪ¬ä¼ļ
    -0.06
    éĢļ常为
    -0.06
    ä¸ĢèĪ¬æľī
    -0.06
    POSITIVE LOGITS
    该åĨħ容
    0.07
    SCO
    0.07
    ateur
    0.07
    quio
    0.07
    ograd
    0.07
    åıĬéĥ¨åĪĨ
    0.07
    à¸Ľà¸£à¸´
    0.06
    -ups
    0.06
    _quote
    0.06
     Citation
    0.06
    Activations Density 0.023%

    No Known Activations