© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8193
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    Negative Logits
     billions
    -0.14
     millions
    -0.10
     billion
    -0.09
     trillion
    -0.09
    999
    -0.09
     agr
    -0.08
     Billion
    -0.08
     lil
    -0.08
    rios
    -0.08
     prohibit
    -0.08
    POSITIVE LOGITS
     amor
    0.12
     sisters
    0.11
     onstage
    0.10
     Therapy
    0.10
     fscanf
    0.10
    UnderTest
    0.10
    !=(
    0.10
     Retrieved
    0.10
     mastur
    0.10
    µ¬
    0.09
    Activations Density 2.819%

    No Known Activations