© 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. 1533
    Prev
    Next
    INDEX
    Explanations

    cells

    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
    noinspection
    -0.25
    .BLL
    -0.21
    æ¥Ŀ
    -0.21
    ä¿®æŃ£
    -0.20
    âĸ¿
    -0.20
    @qq
    -0.20
    endregion
    -0.20
    <message
    -0.19
    .iteritems
    -0.19
    @protocol
    -0.19
    POSITIVE LOGITS
     cells
    0.41
    ç»Ĩèĥŀ
    0.35
     Cells
    0.33
     cell
    0.30
    cells
    0.30
    -cell
    0.28
    æĢ»æķ°
    0.26
    (cells
    0.25
    cell
    0.23
     Cell
    0.22
    Activations Density 2.730%

    No Known Activations