© 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. 32615
    Prev
    Next
    INDEX
    Explanations

    expiration time

    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
    nikov
    -0.07
     nghá»ĭch
    -0.07
    ernal
    -0.06
    娴
    -0.06
    è£Ķ
    -0.06
    ลัà¸ļ
    -0.06
     retrospect
    -0.06
    æķħåIJį
    -0.06
    åıijèĩª
    -0.06
    ä¸Ĭä¸Ģ页
    -0.06
    POSITIVE LOGITS
    `=
    0.09
    æĦıåĽ¾
    0.08
    âĢ¦*
    0.08
     Uncomment
    0.07
    å¸ĮæľĽåľ¨
    0.07
    èįīæ¡Ī
    0.07
     Dall
    0.07
    æĭĵ
    0.07
    tract
    0.07
    ðŁĺī
    0.07
    Activations Density 0.010%

    No Known Activations