© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26958
    Prev
    Next
    INDEX
    Explanations

    st Century

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    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
    argins
    -0.10
     allo
    -0.10
    nds
    -0.09
    rosso
    -0.09
    >manual
    -0.09
    rena
    -0.09
     smear
    -0.09
     Coron
    -0.09
    _INCLUDED
    -0.09
    enis
    -0.09
    POSITIVE LOGITS
     facts
    0.11
     Facts
    0.11
     questions
    0.10
     awesome
    0.10
     Rope
    0.10
     tame
    0.10
    -awesome
    0.09
     hottest
    0.09
     Awesome
    0.09
    eln
    0.09
    Activations Density 0.022%

    No Known Activations