© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3531
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tdown
    -0.23
    emade
    -0.21
    issors
    -0.21
    -NLS
    -0.20
    ------+------+
    -0.19
    okies
    -0.19
    />.
    -0.19
    å·³
    -0.19
    roperties
    -0.19
    éĻĤ
    -0.18
    POSITIVE LOGITS
    ä¸ĵä¸ļä»İäºĭ
    0.23
    åIJ¸å¼ķæĽ´å¤ļ
    0.19
     èĭ¥è¦ģ
    0.19
    ä¸įè¿ľ
    0.19
    ãģĬåĭ§ãĤģ
    0.19
    æľ¬è´¨
    0.18
    ugen
    0.18
    ä¸Ģæŀļ
    0.18
    bove
    0.18
    æ±Łå±±
    0.18
    Activations Density 0.002%

    No Known Activations