© 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. 50828
    Prev
    Next
    INDEX
    Explanations

    hard to

    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
     courtesy
    -0.09
     unre
    -0.09
    rippling
    -0.08
    mega
    -0.08
     Wend
    -0.08
    ÑĢем
    -0.08
     Courtesy
    -0.08
     Hunt
    -0.08
    iber
    -0.07
     hunt
    -0.07
    POSITIVE LOGITS
     enough
    0.16
    (er
    0.11
    ena
    0.11
    (est
    0.11
    /im
    0.11
    ruz
    0.10
     hard
    0.10
    street
    0.10
    ish
    0.10
    ened
    0.10
    Activations Density 0.015%

    No Known Activations