© 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. 3009
    Prev
    Next
    INDEX
    Explanations

    afterwards. at. src. abstract

    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
    anni
    -0.10
    roma
    -0.09
    shirt
    -0.09
    Captain
    -0.09
    !/
    -0.09
    lla
    -0.09
     Noir
    -0.09
     lap
    -0.09
     Phone
    -0.09
    eness
    -0.09
    POSITIVE LOGITS
    ativ
    0.09
    iere
    0.08
     thereafter
    0.07
    Taken
    0.07
     Tem
    0.07
    paste
    0.07
     crack
    0.07
     afterwards
    0.07
     mus
    0.06
     Trem
    0.06
    Activations Density 0.009%

    No Known Activations