© 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. 2773
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
    '^$',
    -0.19
    æ´¨
    -0.19
    éĶĴ
    -0.18
     loggedIn
    -0.18
    ç½ij绾ç§ijæĬĢ
    -0.18
     Nar
    -0.18
    quel
    -0.18
    _accessible
    -0.17
     pubkey
    -0.17
    ç¥Ł
    -0.17
    POSITIVE LOGITS
    apons
    0.25
    âļĹ
    0.25
    uckland
    0.24
    brtc
    0.23
    ðŁĵIJ
    0.23
    -REAL
    0.23
    ðŁļ©
    0.23
    è°ŀ
    0.22
    íĶĦë¡ľê·¸
    0.22
    \/\/
    0.21
    Activations Density 0.003%

    No Known Activations