© 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. 89967
    Prev
    Next
    INDEX
    Explanations

    official titles and personnel

    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
    yo
    -0.12
    -office
    -0.10
    itian
    -0.10
    ya
    -0.10
    office
    -0.10
     office
    -0.09
    teacher
    -0.09
    CAC
    -0.09
    y
    -0.09
    yan
    -0.09
    POSITIVE LOGITS
    hip
    0.11
     bergen
    0.11
    -inv
    0.10
    hips
    0.10
     provoc
    0.10
    -duty
    0.10
    dom
    0.09
     commanding
    0.09
     corps
    0.09
    ystore
    0.09
    Activations Density 0.035%

    No Known Activations