© 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. 3431
    Prev
    Next
    INDEX
    Explanations

    titles and roles

    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
    :'.$
    -0.25
    ][_
    -0.21
     addCriterion
    -0.21
    ién
    -0.20
    ÙħÙĪر
    -0.19
    (ARG
    -0.19
    /XMLSchema
    -0.19
     Atatürk
    -0.19
    =\"#
    -0.19
    économ
    -0.18
    POSITIVE LOGITS
    =".$_
    0.28
    ucher
    0.20
    caff
    0.19
    -ground
    0.19
    æĮīæŶ
    0.19
    uffed
    0.19
    ese
    0.19
    æİ¥åľ°
    0.19
     Griff
    0.18
    éĹŃçݯ
    0.18
    Activations Density 0.001%

    No Known Activations