© 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. 92437
    Prev
    Next
    INDEX
    Explanations

    victor, victoria, victorious

    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
    ep
    -0.10
    e
    -0.09
    er
    -0.09
     uns
    -0.08
    ec
    -0.08
    est
    -0.08
    isman
    -0.07
    ality
    -0.07
    ef
    -0.07
    eh
    -0.07
    POSITIVE LOGITS
    orial
    0.18
    oria
    0.17
    orious
    0.16
    orian
    0.16
    oire
    0.15
    orio
    0.15
    ive
    0.15
    ormsg
    0.14
    ories
    0.14
    engl
    0.14
    Activations Density 0.042%

    No Known Activations