© 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. 92650
    Prev
    Next
    INDEX
    Explanations

    current trends and phenomena

    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
    OID
    -0.10
     bounced
    -0.10
     antique
    -0.10
    chef
    -0.10
     Haley
    -0.10
     traf
    -0.10
     Mega
    -0.10
     Rid
    -0.10
     vintage
    -0.10
     Mej
    -0.10
    POSITIVE LOGITS
     young
    0.14
     teenage
    0.13
     American
    0.12
     contemporary
    0.12
     adolescents
    0.12
     adolescent
    0.12
     omnip
    0.11
     perme
    0.11
     modern
    0.11
     perv
    0.11
    Activations Density 0.156%

    No Known Activations