© 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. 9758
    Prev
    Next
    INDEX
    Explanations

    indices, extension, useless, misleading

    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
    éļ¾å¿ĺ
    -0.08
     cita
    -0.07
    undler
    -0.07
    íģ¼
    -0.07
    illet
    -0.07
    æ´»çļĦ
    -0.07
    åĨħ容æıIJä¾Ľæĸ¹
    -0.07
    encion
    -0.07
    å¦Ħæĥ³
    -0.07
    cident
    -0.07
    POSITIVE LOGITS
    并ä¸į代表
    0.14
    ä¸į代表
    0.12
    并ä¸įèĥ½
    0.12
     misleading
    0.11
    并ä¸įæĦıåij³çĿĢ
    0.11
    ä¸įä¸Ģå®ļ
    0.10
    ä»ħ代表
    0.10
    ä¸įèĥ½ä½ľä¸º
    0.10
    ä¹Łä¸įä¸Ģå®ļ
    0.10
    ä»ħä¾ĽåıĤèĢĥ
    0.09
    Activations Density 0.195%

    No Known Activations