© 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. 3432
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
     sophistic
    -0.23
    BOSE
    -0.23
    strtolower
    -0.22
    èĦ±é¢ĸ
    -0.21
     tph
    -0.20
    _deinit
    -0.20
    ÐŁÐ¾Ð´ÑĢоб
    -0.20
     LENG
    -0.20
    :'.$
    -0.20
    âľİ
    -0.19
    POSITIVE LOGITS
    èĥ¥
    0.20
    TimeString
    0.20
    æ¼ī
    0.20
    DateString
    0.20
    avicon
    0.19
    ausible
    0.19
     ($.
    0.19
    .getElements
    0.19
    æĬķèµĦåŁºéĩij
    0.18
    ê¹ħ
    0.18
    Activations Density 0.032%

    No Known Activations