© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    professions people hold

    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
    /↵↵↵↵
    -0.32
    .nih
    -0.27
    :'.$
    -0.27
    âļĹ
    -0.26
    ,'#
    -0.25
    redient
    -0.25
    /Internal
    -0.25
    stile
    -0.24
    _framework
    -0.24
    linky
    -0.23
    POSITIVE LOGITS
    -turned
    0.24
    ள
    0.19
    åħ¼
    0.19
    ,
    0.19
    **
    0.19
    ——
    0.19
    ä¹ĭä¸Ģ
    0.19
    5
    0.18
    注æĺİåĩºå¤Ħ
    0.18
    --
    0.18
    Activations Density 0.322%

    No Known Activations