© 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. 23768
    Prev
    Next
    INDEX
    Explanations

    locations 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
    æĪĸå°ij
    -0.07
    gege
    -0.07
    è¥
    -0.07
    寺éĻ¢
    -0.07
    走强
    -0.06
    çĶŁæ´»ä¸Ń
    -0.06
    åij¼
    -0.06
    å±ħä½ıåľ¨
    -0.06
    èĢħä¹Ł
    -0.06
    è¿Ļä¹Īåģļ
    -0.06
    POSITIVE LOGITS
     où
    0.08
    åIJĽå®ī
    0.08
    åįĥ人
    0.08
    ãģ¨ãģĵãĤįãģ§
    0.08
    VIP
    0.08
    æİ©
    0.08
    ä½įäºİ
    0.08
     where
    0.08
    apiro
    0.08
     donde
    0.08
    Activations Density 0.726%

    No Known Activations