© 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. 117352
    Prev
    Next
    INDEX
    Explanations

    piece of information

    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
     Herr
    -0.10
     lineup
    -0.09
    Escort
    -0.09
     STACK
    -0.09
     sketch
    -0.09
    acher
    -0.09
    atten
    -0.09
     veto
    -0.09
     sk
    -0.09
     Naj
    -0.09
    POSITIVE LOGITS
     Hak
    0.10
     [
    0.10
    eken
    0.09
     gaz
    0.09
     *[
    0.09
    stan
    0.09
    quote
    0.09
     GP
    0.08
     exchanges
    0.08
    udev
    0.08
    Activations Density 0.001%

    No Known Activations