© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8919
    Prev
    Next
    INDEX
    Explanations

    delayed by, manipulated in, bank address, piece height

    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
    ulich
    -0.07
    <|box_end|>
    -0.07
    FPS
    -0.07
    =>'
    -0.07
    icker
    -0.07
    æĪijæľīä¸Ģ个
    -0.07
    åħįè´¹åľ¨çº¿
    -0.07
    rieb
    -0.07
    æijĺç¼ĸ
    -0.07
    "io
    -0.07
    POSITIVE LOGITS
     respective
    0.07
    è¿ĺæľª
    0.07
    æѤæŶ
    0.07
    å·²ç»ıä»İ
    0.07
    åį³å°Ĩ
    0.07
    åħĪåīį
    0.07
    æĸ°ä¸Ģè½®
    0.06
    å¦Ĥä¸Ĭ
    0.06
    对è§Ĵ
    0.06
    æľīä½Ļ
    0.06
    Activations Density 0.011%

    No Known Activations