© 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. 2532
    Prev
    Next
    INDEX
    Explanations

    recent academic papers

    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
    ponce
    -0.21
    è§ĩ
    -0.20
    libft
    -0.20
    opal
    -0.20
    ?>↵↵↵
    -0.19
    第äºĮç§į
    -0.19
    è®°èĢħäºĨ解
    -0.18
    éĺ¶æ¢¯
    -0.18
    {!!
    -0.18
    è¿Ļ两ç§į
    -0.18
    POSITIVE LOGITS
    :disable
    0.24
    :;↵
    0.23
    è¿Ħ
    0.21
     backpage
    0.20
    é¾ĥ
    0.20
    大åħ¨
    0.20
    GLOSS
    0.20
    /vnd
    0.19
    .'_
    0.19
    åĨ°æ·ĩ
    0.19
    Activations Density 0.093%

    No Known Activations