© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 58
    Prev
    Next
    INDEX
    Explanations

    code contributions

    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
     LINUX
    -0.23
    _datos
    -0.23
    Configurer
    -0.23
     LUA
    -0.23
     tumblr
    -0.22
    女æĢ§æľĭåıĭ
    -0.22
     Länder
    -0.22
     insets
    -0.21
    /***/
    -0.21
    _detalle
    -0.21
    POSITIVE LOGITS
    :animated
    0.28
    ï¼ģ');↵
    0.27
    redirectTo
    0.26
    ðŁĵIJ
    0.26
    anmar
    0.25
    #aa
    0.25
    社åįĢ
    0.24
    .CV
    0.24
    æŁ¥çľĭ详æĥħ
    0.24
    contrib
    0.23
    Activations Density 3.552%

    No Known Activations