© 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. 2488
    Prev
    Next
    INDEX
    Explanations

    numbers, math, technical

    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
    ','');↵
    -0.29
    @student
    -0.26
    åĹIJ
    -0.25
    aeda
    -0.24
    esktop
    -0.24
    ):?>↵
    -0.24
    ","#
    -0.24
    presso
    -0.24
    -football
    -0.23
    zbek
    -0.23
    POSITIVE LOGITS
    ward
    0.19
     "','
    0.18
     onto
    0.18
    à¹Ĥà¸Ńà¸ģา
    0.18
    è·¯è¿ĩ
    0.18
    uuid
    0.18
     Sanford
    0.17
    æľīå¾Ī大
    0.17
    æ¨Ĺ
    0.17
    ä½łçľĭ
    0.17
    Activations Density 0.004%

    No Known Activations