© 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. 87926
    Prev
    Next
    INDEX
    Explanations

    notice file distributed

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Pokémon
    -0.11
     tú
    -0.11
     naï
    -0.11
     Québec
    -0.10
    ún
    -0.10
     José
    -0.09
     âĤ¹
    -0.09
     ré
    -0.09
    upp
    -0.09
    âĢij
    -0.09
    POSITIVE LOGITS
    mailto
    0.12
     emailing
    0.11
    Reply
    0.11
     inse
    0.11
    èģĶç³»
    0.10
     fuer
    0.10
    riere
    0.10
    Tel
    0.10
     Tel
    0.10
     fatt
    0.10
    Activations Density 0.010%

    No Known Activations