© 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. 45119
    Prev
    Next
    INDEX
    Explanations

    professions or places

    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
    esto
    -0.08
    esta
    -0.07
    ieres
    -0.07
    ç»Ħç»ĩéĥ¨
    -0.07
    ä¸į管
    -0.07
    ronic
    -0.07
    çī©åĴĮ
    -0.07
    ÑĭÑħ
    -0.07
    åªĴ
    -0.06
    èµ·æĿ¥
    -0.06
    POSITIVE LOGITS
    åıĪæĪĸèĢħ
    0.10
    亦æĪĸæĺ¯
    0.10
    æĬijæĪĸ
    0.08
    æĬij
    0.08
    ä¹Łåı¯èĥ½æĺ¯
    0.08
    ctal
    0.07
    æĽ´çĶŁ
    0.07
     kali
    0.07
    æĥ³çŁ¥éģĵ
    0.07
    äºĨä¸įèµ·
    0.07
    Activations Density 0.019%

    No Known Activations