© 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. 1919
    Prev
    Next
    INDEX
    Explanations

    say "}"

    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
    缣
    -0.21
    åĵ§
    -0.21
    .DataAccess
    -0.21
     ÑĢаÑģпÑĢоÑģÑĤÑĢанен
    -0.21
     ));↵↵
    -0.20
    樯
    -0.20
    одеÑĢж
    -0.19
     ));č↵
    -0.19
     seins
    -0.19
    addGroup
    -0.19
    POSITIVE LOGITS
    #endif
    0.31
     endregion
    0.29
    @end
    0.25
    -Feb
    0.25
    IGIN
    0.23
    ãĢĭ
    0.23
    endregion
    0.22
     breat
    0.22
    createForm
    0.22
     avalia
    0.21
    Activations Density 1.036%

    No Known Activations