© 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. 25086
    Prev
    Next
    INDEX
    Explanations

    something like

    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
     fifteen
    -0.09
     seven
    -0.09
    imei
    -0.09
     five
    -0.09
     Licence
    -0.09
     hereby
    -0.08
    seven
    -0.08
     thirty
    -0.08
    âĹı
    -0.08
     Maher
    -0.08
    POSITIVE LOGITS
     (?)
    0.42
     somehow
    0.36
     somewhere
    0.35
    (?
    0.34
     (?
    0.34
     something
    0.29
     apparently
    0.26
    something
    0.26
     somew
    0.25
     Somehow
    0.25
    Activations Density 0.951%

    No Known Activations