© 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. 32762
    Prev
    Next
    INDEX
    Explanations

    competitive, infuriating, creepy, hot

    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
     Artis
    -0.09
    æ»¡çľ¼
    -0.08
    åĩĨäºĪ
    -0.08
     Romano
    -0.08
    jaman
    -0.08
    ergie
    -0.08
    åѦåĪ°äºĨå¾Īå¤ļ
    -0.08
    åıĺå¾ĹæĽ´åĬł
    -0.07
    Äĥm
    -0.07
    igni
    -0.07
    POSITIVE LOGITS
    .Thread
    0.06
     yet
    0.06
     level
    0.06
    æ³Ĭ
    0.06
    unta
    0.06
     fail
    0.06
    elligent
    0.06
    深度åŃ¦ä¹ł
    0.06
    er
    0.06
    ç»ĵæŀĦ设计
    0.06
    Activations Density 0.001%

    No Known Activations