© 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. 2983
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    CLUDING
    -0.23
    æ¤ĭ
    -0.22
    'Neill
    -0.21
    atori
    -0.20
    <=(
    -0.20
    ALLERY
    -0.20
    frei
    -0.20
    æķŀ
    -0.19
    (ErrorMessage
    -0.19
    urm
    -0.19
    POSITIVE LOGITS
     vÃŃt
    0.22
    logan
    0.21
     cerco
    0.20
     inve
    0.20
    sworth
    0.19
    егиÑģÑĤ
    0.18
    客åķĨ
    0.18
    %"><
    0.18
    åĢ¨
    0.18
    _decrypt
    0.18
    Activations Density 0.160%

    No Known Activations