© 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. 1784
    Prev
    Next
    INDEX
    Explanations

    word beginnings

    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
    	Copyright
    -0.10
    ÑħÑĢан
    -0.10
     ('\
    -0.09
    avanaugh
    -0.09
    plemented
    -0.09
    ẩu
    -0.08
    дÑĢеÑģ
    -0.08
    ramid
    -0.08
    agate
    -0.08
    antaged
    -0.08
    POSITIVE LOGITS
    <|fim_suffix|>
    0.14
    ÂŃ
    0.12
    <|fim_middle|>
    0.12
    odka
    0.10
    0.09
     Likes
    0.09
     dul
    0.08
    /or
    0.08
    ек
    0.08
    и
    0.08
    Activations Density 3.245%

    No Known Activations