© 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. 50374
    Prev
    Next
    INDEX
    Explanations

    application and app versions

    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
     indoors
    -0.09
     Jordan
    -0.08
    ernet
    -0.08
    .online
    -0.08
     hobby
    -0.08
     Trainer
    -0.08
     ac
    -0.08
     Lor
    -0.08
    ropa
    -0.08
    cko
    -0.08
    POSITIVE LOGITS
     convenient
    0.15
     unofficial
    0.15
     officially
    0.14
     mirror
    0.14
    official
    0.13
     official
    0.13
     sleek
    0.13
     version
    0.13
     oficial
    0.13
     counterpart
    0.12
    Activations Density 0.477%

    No Known Activations