© 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. 8195
    Prev
    Next
    INDEX
    Explanations

    free, only, price, format

    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
    asto
    -0.12
    ihan
    -0.10
     screenshots
    -0.10
     Downs
    -0.10
    ija
    -0.10
     contacts
    -0.09
     bq
    -0.09
    ocity
    -0.09
    ë¦Ħ
    -0.09
    abox
    -0.09
    POSITIVE LOGITS
     adam
    0.09
     Yas
    0.09
     priv
    0.08
     Adam
    0.08
     convin
    0.08
     underlying
    0.08
     âľĵ
    0.08
    itan
    0.08
     only
    0.08
     jan
    0.08
    Activations Density 0.076%

    No Known Activations