© 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. 7634
    Prev
    Next
    INDEX
    Explanations

    names starting with common European prefixes

    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
     Diane
    -0.12
     Elaine
    -0.11
     Annie
    -0.11
     Margaret
    -0.11
    reuse
    -0.10
    cona
    -0.10
     Helen
    -0.10
    itura
    -0.10
     herself
    -0.10
     prima
    -0.10
    POSITIVE LOGITS
    fgang
    0.18
    useppe
    0.13
    éric
    0.13
    fried
    0.13
    adius
    0.12
     handsome
    0.12
    jandro
    0.12
    bert
    0.12
    ildo
    0.12
    isl
    0.11
    Activations Density 0.972%

    No Known Activations