© 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. 3005
    Prev
    Next
    INDEX
    Explanations

    able

    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
    IALIZED
    -0.23
    å®ļå¾ĭ
    -0.20
    åѤç«ĭ
    -0.20
    TG
    -0.19
    \/\/
    -0.19
    å¹²äºĭåĪĽä¸ļ
    -0.19
    è¿Ľè¡Įåħ¨éĿ¢
    -0.19
    çĥ«
    -0.19
    as
    -0.18
    اÙĪÙĬØ©
    -0.18
    POSITIVE LOGITS
    SqlParameter
    0.29
    ainting
    0.28
    acades
    0.27
    )((((
    0.27
    @student
    0.26
    AspNet
    0.25
    ")));
    0.25
    outu
    0.25
    uropean
    0.25
    -bodied
    0.24
    Activations Density 0.109%

    No Known Activations