© 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. 4249
    Prev
    Next
    INDEX
    Explanations

    units of measurement and quantities

    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
     incorpor
    -0.10
    agli
    -0.09
     Nel
    -0.09
    elf
    -0.09
    -wrapper
    -0.09
    ialog
    -0.09
     Su
    -0.09
    /Edit
    -0.09
    ipa
    -0.09
     grote
    -0.08
    POSITIVE LOGITS
    otto
    0.10
     per
    0.10
     Mayo
    0.09
    /thread
    0.09
     fre
    0.09
     knowingly
    0.09
     instant
    0.09
     Ernst
    0.09
    unday
    0.09
    illion
    0.08
    Activations Density 0.493%

    No Known Activations