© 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. 46211
    Prev
    Next
    INDEX
    Explanations

    only thing I

    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
     anywhere
    -0.13
     any
    -0.11
     anybody
    -0.11
     whatsoever
    -0.10
     anyone
    -0.10
     anymore
    -0.10
     anything
    -0.09
    ANY
    -0.09
    any
    -0.09
     PT
    -0.09
    POSITIVE LOGITS
    edd
    0.11
    ariat
    0.10
    èĥ½
    0.10
     sole
    0.10
     closest
    0.10
    least
    0.10
     vra
    0.10
     Vib
    0.09
     thing
    0.09
     abi
    0.09
    Activations Density 0.073%

    No Known Activations