© 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. 26644
    Prev
    Next
    INDEX
    Explanations

    boolean values

    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
    许许å¤ļå¤ļçļĦ
    -0.07
    apot
    -0.07
    (?)
    -0.06
    kilde
    -0.06
    箩
    -0.06
    PropertyValue
    -0.06
    agno
    -0.06
    称åij¼
    -0.06
    .@
    -0.06
    ີ
    -0.06
    POSITIVE LOGITS
    åİĨå¹´çľŁé¢ĺ
    0.07
    uez
    0.07
    æĮīæľĪ
    0.07
    ë§ī
    0.07
     subsidized
    0.07
    rody
    0.07
    лев
    0.06
    æľīéĻIJ
    0.06
    åıĪæĺ¯ä¸Ģå¹´
    0.06
    udent
    0.06
    Activations Density 0.021%

    No Known Activations