© 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. 7868
    Prev
    Next
    INDEX
    Explanations

    social english and human behavior

    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
    æīĢåѦä¸ĵä¸ļ
    -0.07
    ãĥĥãĤ·
    -0.07
    æľī计åĪĴ
    -0.07
     misguided
    -0.07
     separat
    -0.07
    å¦Ĥèį¼
    -0.07
    èij©
    -0.07
    åĪĽæĸ°æĦıè¯Ĩ
    -0.07
     systematic
    -0.07
    antro
    -0.07
    POSITIVE LOGITS
     unofficial
    0.10
     informal
    0.10
    人æĥħ
    0.09
    å®ŀéĻħæĵįä½ľ
    0.09
     lived
    0.09
     contextual
    0.09
    羣å®ŀ
    0.09
     tac
    0.09
    é²ľæ´»
    0.08
     context
    0.08
    Activations Density 0.132%

    No Known Activations