© 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. 3857
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    благо
    -0.28
     dikke
    -0.26
    建档ç«ĭ
    -0.26
    ]={↵
    -0.25
    AndView
    -0.25
    ç¡ļ
    -0.24
    翾
    -0.23
    ä¸įåı¯æĢĿ
    -0.23
    reactstrap
    -0.23
    :;↵
    -0.22
    POSITIVE LOGITS
     {});↵↵
    0.27
    l
    0.21
    èĵĬ
    0.20
    reetings
    0.20
    isto
    0.19
    -t
    0.19
     mListener
    0.18
    åŀĴ
    0.18
    t
    0.18
    çĶ¨
    0.18
    Activations Density 0.001%

    No Known Activations