© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49321
    Prev
    Next
    INDEX
    Explanations

    Libre, Source, C++, EasyRPG, Care, subject, List, Money, Disc, Bopp

    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
    ÃĤ
    -0.11
    ioxide
    -0.11
     COMPUTER
    -0.10
     uncon
    -0.10
    ober
    -0.10
     Scotch
    -0.10
    olley
    -0.10
    (sp
    -0.10
    <?,
    -0.10
    bindings
    -0.10
    POSITIVE LOGITS
    azo
    0.08
     Fur
    0.07
     searchable
    0.07
     also
    0.07
     discour
    0.07
     additionally
    0.07
     lut
    0.07
     backstage
    0.07
    /set
    0.07
     anim
    0.07
    Activations Density 0.003%

    No Known Activations