© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 852
    Prev
    Next
    INDEX
    Explanations

    proteinase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abilities
    -0.07
    grily
    -0.06
     debug
    -0.06
    \_
    -0.06
     nud
    -0.06
    whel
    -0.06
    )(((
    -0.06
    gles
    -0.06
     Tomb
    -0.06
    isser
    -0.06
    POSITIVE LOGITS
     sui
    0.11
     öff
    0.11
     conce
    0.10
    clone
    0.10
    æŀ
    0.10
    hip
    0.10
    (of
    0.10
    :inline
    0.10
    faker
    0.10
     "('
    0.10
    Activations Density 3.664%

    No Known Activations