© 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. 1958
    Prev
    Next
    INDEX
    Explanations

    body systems

    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
    chedulers
    -0.28
    .deepEqual
    -0.21
    ovenant
    -0.21
    /effects
    -0.20
    /stretch
    -0.20
    .initializeApp
    -0.20
    SSIP
    -0.20
    èĦĺ
    -0.20
    佬
    -0.19
    .Multiline
    -0.19
    POSITIVE LOGITS
    åĨħçļĦ
    0.53
    éĩĮçļĦ
    0.43
    ä¸ŃçļĦ
    0.42
    -wide
    0.40
    éĩĮ
    0.34
    ä¸Ńæľī
    0.31
    wide
    0.30
    ä¸ŃåŃĺåľ¨çļĦ
    0.28
    裡
    0.28
    åĨħ
    0.28
    Activations Density 8.351%

    No Known Activations