© 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. 4469
    Prev
    Next
    INDEX
    Explanations

    Roman numerals or abbreviations like IV, IVF, Ivory

    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
     Dynasty
    -0.08
     customizable
    -0.08
     segreg
    -0.07
     customization
    -0.07
     instruct
    -0.07
     informed
    -0.07
     Bradford
    -0.07
     refactor
    -0.07
     Ellis
    -0.07
     dynasty
    -0.07
    POSITIVE LOGITS
    ê²Į
    0.11
     fare
    0.11
    medium
    0.11
    caret
    0.11
     warmed
    0.11
     medium
    0.11
    elu
    0.10
     deliberate
    0.10
    endo
    0.10
    rus
    0.10
    Activations Density 0.001%

    No Known Activations