© 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. 30534
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
     presumably
    -0.09
     hopefully
    -0.08
    æĩ¿
    -0.08
    itera
    -0.08
     typically
    -0.07
    typically
    -0.07
    èĩ³ä»Ĭå·²
    -0.07
    éĢļ常
    -0.07
    usually
    -0.07
     usually
    -0.07
    POSITIVE LOGITS
     somehow
    0.13
    æľīåħ¶ä»ĸ
    0.08
    oor
    0.08
     irgendwie
    0.08
     fosse
    0.08
    æīį对
    0.08
    æł¹æľ¬ä¸įæĺ¯
    0.08
    è¿ĺæľīåħ¶ä»ĸ
    0.08
    sov
    0.08
    è¿ĺä¸įå¤Ł
    0.08
    Activations Density 0.017%

    No Known Activations