© 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. 1599
    Prev
    Next
    INDEX
    Explanations

    patent numbers and citations

    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
    akup
    -0.07
    oki
    -0.07
    aje
    -0.07
    èĦ¯
    -0.07
    upo
    -0.06
    &E
    -0.06
    รส
    -0.06
    hdr
    -0.06
     esk
    -0.06
    rez
    -0.06
    POSITIVE LOGITS
    er
    0.07
    _none
    0.07
    erule
    0.06
    åİĭåĻ¨
    0.06
    ernal
    0.06
    вÑijÑĢ
    0.06
    å¦ĵ
    0.06
    ivin
    0.06
    carat
    0.06
     numbered
    0.06
    Activations Density 0.332%

    No Known Activations