© 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. 28140
    Prev
    Next
    INDEX
    Explanations

    state of being or positioning

    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
    æĺ¥æĿ¥
    -0.08
    æĪij们è¿Ļ个
    -0.08
     cuyos
    -0.07
    ASSES
    -0.07
    orni
    -0.07
    ä½łè¿Ļ个
    -0.07
     Ayd
    -0.07
    å¥Īä½ķ
    -0.07
    æĪij身边
    -0.07
     Sán
    -0.07
    POSITIVE LOGITS
    个ä¸įåģľ
    0.06
    åı¯æľŁ
    0.06
    izzo
    0.06
    åĴĮåIJİ
    0.06
     Barrett
    0.06
    ä¸įå¤ĸ
    0.06
    ä»İèĢĮè¾¾åĪ°
    0.06
     zip
    0.06
    æĥħåĨµåĴĮ
    0.06
    lobs
    0.06
    Activations Density 0.464%

    No Known Activations