© 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. 48914
    Prev
    Next
    INDEX
    Explanations

    shift or switch

    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
    INES
    -0.08
    ghan
    -0.07
    à¸ģำ
    -0.07
    çĥŃæIJľè¯į
    -0.07
    æīĢ欲
    -0.07
    æľ¬ç½ijç«Ļ
    -0.07
     alcance
    -0.07
    nes
    -0.07
    ffects
    -0.06
    è¾¾åĪ°
    -0.06
    POSITIVE LOGITS
    转åĪ°
    0.09
     onto
    0.09
     focus
    0.09
    转åIJij
    0.08
    转为
    0.08
    éĩįå¿ĥ
    0.08
     Shift
    0.08
     shifted
    0.08
    focus
    0.08
    (shift
    0.08
    Activations Density 0.132%

    No Known Activations