© 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. 27580
    Prev
    Next
    INDEX
    Explanations

    weight and measurements

    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
    å¦Īå¦Ī们
    -0.08
    ither
    -0.07
     заÑĢ
    -0.07
    ä¸ĩä¸Ī
    -0.07
    trom
    -0.07
    inato
    -0.07
     Marriage
    -0.07
     landscape
    -0.06
    æīĭåĬ¿
    -0.06
    油管
    -0.06
    POSITIVE LOGITS
    éĩįéĩı
    0.12
     mass
    0.11
    çļĦéĩįéĩı
    0.11
     masses
    0.11
     weight
    0.11
     kg
    0.11
     маÑģÑģой
    0.11
    ä½ĵéĩį
    0.11
     weighs
    0.11
    weight
    0.11
    Activations Density 0.010%

    No Known Activations