© 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. 3125
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
    åĻ¨åħ·
    -0.20
    åĬłåĢį
    -0.20
    _INFINITY
    -0.19
    aycast
    -0.19
    æµ¥
    -0.19
    rich
    -0.18
    _flg
    -0.18
    åĪĩæĪIJ
    -0.18
    被人
    -0.18
    Į
    -0.18
    POSITIVE LOGITS
    hecy
    0.25
    č↵↵
    0.23
    :maj
    0.21
    ','=',$
    0.21
    æĢ»èĢĮè¨Ģ
    0.21
    èݨ
    0.20
    acular
    0.20
     perpetr
    0.20
    egis
    0.20
     Ấ
    0.20
    Activations Density 0.088%

    No Known Activations