© 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. 2692
    Prev
    Next
    INDEX
    Explanations

    /LICENSE

    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
    (strpos
    -0.22
    沪æĮĩ
    -0.20
    IRST
    -0.20
    Specifier
    -0.20
    .getHost
    -0.19
    æļĦ
    -0.18
     universal
    -0.18
    imat
    -0.18
    ispens
    -0.18
     Carry
    -0.18
    POSITIVE LOGITS
    ].'
    0.22
     UITapGestureRecognizer
    0.21
     embod
    0.21
     busty
    0.21
    ropolis
    0.20
     )↵↵↵↵↵↵↵↵
    0.20
    uxtap
    0.20
    .getOwnProperty
    0.20
    家éĥ½çŁ¥éģĵ
    0.19
    uguay
    0.19
    Activations Density 0.016%

    No Known Activations