© 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. 117339
    Prev
    Next
    INDEX
    Explanations

    accomplices and accused

    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
    tex
    -0.09
    ivor
    -0.09
    ocity
    -0.09
    tout
    -0.09
    adows
    -0.09
    ĸ
    -0.09
    ulan
    -0.09
     tex
    -0.09
     factual
    -0.09
    urret
    -0.08
    POSITIVE LOGITS
    sworth
    0.09
     Universities
    0.09
    ied
    0.09
     accomp
    0.09
    ged
    0.09
    orz
    0.09
     Verd
    0.09
     gems
    0.09
    èĢ
    0.09
    uft
    0.09
    Activations Density 0.001%

    No Known Activations