© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2259
    Prev
    Next
    INDEX
    Explanations

    colon

    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
    manın
    -0.28
    mayı
    -0.22
    ={`${
    -0.21
    .ibatis
    -0.21
    ((&
    -0.20
    ailable
    -0.20
    ButtonItem
    -0.20
    commended
    -0.19
    privation
    -0.19
    ä½ĵèĤ²åľ¨çº¿
    -0.19
    POSITIVE LOGITS
    agascar
    0.22
     fucks
    0.20
     RoundedRectangle
    0.20
    lette
    0.20
    enberg
    0.20
    burg
    0.19
    NSS
    0.19
    é©¿
    0.19
    incinnati
    0.19
    ennifer
    0.19
    Activations Density 0.009%

    No Known Activations