© 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. 3165
    Prev
    Next
    INDEX
    Explanations

    text fragments

    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
     typingsSlinky
    -0.23
    DET
    -0.22
    FER
    -0.21
    ðŁĺİ
    -0.20
     seedu
    -0.20
    меÑīен
    -0.20
    abcdefghijklmnop
    -0.20
    ?>/
    -0.20
    è¯ģ
    -0.20
    }↵↵↵↵↵↵
    -0.20
    POSITIVE LOGITS
     Interracial
    0.28
    kea
    0.25
     Parenthood
    0.23
    ylvania
    0.23
     cuckold
    0.23
     Ä°n
    0.23
    urovision
    0.22
    á¹¢
    0.22
    -ves
    0.22
    /Dk
    0.22
    Activations Density 0.001%

    No Known Activations