© 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. 3823
    Prev
    Next
    INDEX
    Explanations

    as

    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
     seedu
    -0.25
    >{"
    -0.24
    arrière
    -0.23
    keiten
    -0.21
    åŃ£åIJİ
    -0.20
    åİ©
    -0.20
    abis
    -0.20
    Runnable
    -0.20
    ÅĤat
    -0.20
     Erectile
    -0.19
    POSITIVE LOGITS
    继ç»Ń
    0.24
    æİ¥è¿ij
    0.23
     continue
    0.23
    éĢ¼è¿ij
    0.22
     ne
    0.22
     CircularProgress
    0.21
    è¶ĬæĿ¥è¶Ĭ
    0.20
    æĢį
    0.20
     progresses
    0.20
    è¿Ľè¡Į
    0.20
    Activations Density 0.291%

    No Known Activations