© 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. 15601
    Prev
    Next
    INDEX
    Explanations

    highlights and points out

    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
    ä¸ĢåĽŀäºĭ
    -0.09
    åĵĪæĭī
    -0.08
    ysÅĤ
    -0.07
    inals
    -0.07
    ity
    -0.07
    轰鸣
    -0.07
    ecure
    -0.07
    ijn
    -0.07
    ulfilled
    -0.07
    weiler
    -0.07
    POSITIVE LOGITS
    åī¤
    0.09
    人çī©
    0.09
    人çī©çļĦ
    0.09
    eness
    0.08
    ging
    0.08
    à¸Ĭัà¸Ķ
    0.07
    à¹Ģรืà¹Īà¸Ńยà¹Ĩ
    0.07
    ulah
    0.07
    on
    0.07
     differences
    0.07
    Activations Density 0.031%

    No Known Activations