© 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. 63586
    Prev
    Next
    INDEX
    Explanations

    negative events or occurrences

    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
    ValueCollection
    -0.07
    schau
    -0.07
     vzn
    -0.07
    eah
    -0.07
     underrated
    -0.07
    leter
    -0.07
    éķ¿å¹´
    -0.06
    éĽ¨éľ²
    -0.06
     ruled
    -0.06
    ä¸ĢæĪ·
    -0.06
    POSITIVE LOGITS
    éĤ£ä¸¤ä¸ª
    0.09
    ãģĤãģ®
    0.07
    æľīäºĨä¸Ģ个
    0.07
    é£İæ³¢
    0.07
    unc
    0.07
    cd
    0.06
    éĤ£ä¹Ī大
    0.06
    bak
    0.06
    ä¸į该
    0.06
    éĤ£ä¹Īå¤ļ
    0.06
    Activations Density 0.374%

    No Known Activations