© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21940
    Prev
    Next
    INDEX
    Explanations

    intend to approve

    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
    åİļå¾·
    -0.08
    idget
    -0.08
    é¦Ī
    -0.07
    æľīçĤ¹åĥı
    -0.07
    uilder
    -0.07
    纳æĸ¯
    -0.07
    heen
    -0.07
    .Promise
    -0.07
    ngx
    -0.07
     mend
    -0.07
    POSITIVE LOGITS
    æĦıåľ¨
    0.10
     intended
    0.10
    æĦıåĽ¾
    0.09
    ä»ĸ们认为
    0.09
    认为
    0.08
     intend
    0.08
     intends
    0.08
     подÑĢазÑĥмев
    0.07
     simply
    0.07
     EITHER
    0.07
    Activations Density 0.003%

    No Known Activations