© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4012
    Prev
    Next
    INDEX
    Explanations

    Quoted text or 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
     masturbating
    -0.23
    afür
    -0.22
    upertino
    -0.21
    ?"↵↵↵↵
    -0.19
    ç»ĻæĪij们
    -0.18
    rang
    -0.18
    ¾ç¤º
    -0.18
    iquement
    -0.18
    écoute
    -0.18
     Magnum
    -0.18
    POSITIVE LOGITS
    -ln
    0.28
    öyle
    0.22
    glfw
    0.22
    çİ
    0.21
    %X
    0.21
    openh
    0.21
    ntl
    0.20
    :request
    0.20
    }_${
    0.20
    éŀ²
    0.20
    Activations Density 0.001%

    No Known Activations