© 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. 92417
    Prev
    Next
    INDEX
    Explanations

    phone numbers and messages

    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
     Cain
    -0.08
    ftime
    -0.08
     chic
    -0.08
     Cre
    -0.07
    ored
    -0.07
    robe
    -0.07
    Neal
    -0.06
     strong
    -0.06
     Deleted
    -0.06
     distra
    -0.06
    POSITIVE LOGITS
     booth
    0.15
    éfono
    0.15
    calls
    0.15
     handset
    0.15
     booths
    0.14
    ë²Īíĺ¸
    0.13
    /table
    0.13
    /email
    0.13
     Booth
    0.12
    cia
    0.12
    Activations Density 0.073%

    No Known Activations