© 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. 55788
    Prev
    Next
    INDEX
    Explanations

    [@citation]s

    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
    asn
    -0.10
    ipy
    -0.10
    istra
    -0.10
    .reason
    -0.10
    аÑĩ
    -0.10
    adoo
    -0.10
    undry
    -0.09
    andatory
    -0.09
    asio
    -0.09
    à¯į
    -0.09
    POSITIVE LOGITS
     Conrad
    0.08
    uru
    0.08
    atin
    0.07
    ods
    0.07
     Wick
    0.07
    lap
    0.07
     Mer
    0.07
     contours
    0.07
    /std
    0.07
     em
    0.07
    Activations Density 0.001%

    No Known Activations