© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    implications, let's

    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
    çļĦå¿ĥ声
    -0.09
    ä¸įæĸĻ
    -0.08
    家æĿij
    -0.07
    请èģĶç³»æĪij们
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    é£İéĻ©çĽijæݧ
    -0.07
    ulet
    -0.07
     subparagraph
    -0.07
    !
    -0.07
    .NewReader
    -0.07
    POSITIVE LOGITS
    éĻĦ
    0.08
    åı¦å¤ĸ
    0.08
    éĻĦä¸Ĭ
    0.08
     szk
    0.08
     اÙĦتÙģ
    0.07
    aggi
    0.07
    IMO
    0.07
    ignan
    0.07
    amal
    0.07
    åĶ¯ä¸Ģ
    0.07
    Activations Density 0.872%

    No Known Activations