© 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. 22057
    Prev
    Next
    INDEX
    Explanations

    legal and political terms

    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
    aign
    -0.08
    èĥ½ä»¥
    -0.07
    kees
    -0.07
    .Builder
    -0.07
    omics
    -0.07
    ائÙĨ
    -0.07
    ä¸į足以
    -0.07
    ätz
    -0.07
    apura
    -0.07
    æĹ¥ä»¥
    -0.06
    POSITIVE LOGITS
     traditionally
    0.09
    çļĦä¼łç»Ł
    0.08
    except
    0.08
    èĩªåı¤
    0.07
    åľ¨æŁIJäºĽ
    0.07
    èĻ½çĦ¶åľ¨
    0.07
     Trad
    0.07
     ÑĤÑĢадиÑĨионно
    0.07
     universally
    0.07
    è¿Ļåľ¨
    0.07
    Activations Density 0.124%

    No Known Activations