© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1463
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    个å¤ļ
    -0.25
    åıĸåĨ³
    -0.24
    åľ¨è¿ĩ渡
    -0.24
    ä½Ĩä¸įéĻIJ
    -0.24
    èĢĮ导èĩ´
    -0.24
    çĶŃ
    -0.24
    çĿ¨
    -0.22
    ä¸Ģ个èģĮä¸ļ
    -0.22
    æĢ§ä»·
    -0.21
    esteem
    -0.21
    POSITIVE LOGITS
    :
    0.43
    ï¼ļ
    0.35
     :
    0.29
     bigot
    0.29
     ï¼ļ
    0.27
     is
    0.25
     assh
    0.25
    privation
    0.24
    oriously
    0.23
     -
    0.23
    Activations Density 6.201%

    No Known Activations