© 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. 113740
    Prev
    Next
    INDEX
    Explanations

    free services and registration

    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
     badly
    -0.10
     discounts
    -0.10
     priced
    -0.10
     Rescue
    -0.10
     discounted
    -0.10
    gratis
    -0.10
     Jaw
    -0.09
     Meals
    -0.09
    Paid
    -0.09
    stream
    -0.09
    POSITIVE LOGITS
    alah
    0.09
     Encore
    0.09
    apos
    0.09
     Cumberland
    0.09
     Verg
    0.09
     tracer
    0.09
     transl
    0.09
     filler
    0.09
    /misc
    0.09
    ella
    0.09
    Activations Density 0.020%

    No Known Activations