© 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. 41207
    Prev
    Next
    INDEX
    Explanations

    css layout and alignment

    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
    abia
    -0.08
    urant
    -0.07
    LB
    -0.07
    [++
    -0.07
    æĹŃ
    -0.07
     xô
    -0.07
    ä¼´ä½ł
    -0.07
    empre
    -0.06
    urz
    -0.06
    Cô
    -0.06
    POSITIVE LOGITS
    æĪijä¸Ģ个
    0.07
     Distribu
    0.07
    eling
    0.07
     DISCLAIMER
    0.07
    uga
    0.07
    åĪĨå¸ĥ
    0.07
    _ser
    0.07
     Kushner
    0.07
     Hung
    0.07
    áĢĦáĢºáĢ¸
    0.07
    Activations Density 0.054%

    No Known Activations