© 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. 64792
    Prev
    Next
    INDEX
    Explanations

    URLs and metadata labels

    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
    onial
    -0.08
    çīĪæĿĥå±ŀäºİ
    -0.07
    mpr
    -0.07
    atee
    -0.07
     disappoint
    -0.06
    enko
    -0.06
    omat
    -0.06
    èĸĦ
    -0.06
    æŀī
    -0.06
    omag
    -0.06
    POSITIVE LOGITS
    éĥ¨ç»ıçIJĨ
    0.07
    shire
    0.07
    atre
    0.07
    иÑĤелÑĮÑģÑĤва
    0.07
    ç¶Ļ
    0.07
    被ç½ļ
    0.06
    nit
    0.06
    綱
    0.06
    isky
    0.06
    æ¶ī
    0.06
    Activations Density 0.012%

    No Known Activations