© 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. 3792
    Prev
    Next
    INDEX
    Explanations

    EDIT

    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
    eldom
    -0.22
    è·ĥ
    -0.19
     Kur
    -0.19
    éĤ£éĩĮ
    -0.18
    æĵ¢
    -0.18
    欲
    -0.18
    "group
    -0.18
    xampp
    -0.17
     yours
    -0.17
     odd
    -0.17
    POSITIVE LOGITS
     cellForRowAtIndexPath
    0.29
    -scalable
    0.25
     update
    0.23
    .IsNullOr
    0.23
    ccoli
    0.22
     clarification
    0.22
    /update
    0.22
    .update
    0.22
     clarified
    0.22
    éĤ¯
    0.22
    Activations Density 0.311%

    No Known Activations