© 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. 92515
    Prev
    Next
    INDEX
    Explanations

    polynomial, status, languages, operator, construct, Exception, Politics

    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
    :</
    -0.13
    ...",↵
    -0.12
    Âł
    -0.12
    !",↵
    -0.12
    ?"↵↵↵↵
    -0.11
    __":↵
    -0.11
    ():↵
    -0.11
    :",↵
    -0.11
    .*;↵↵
    -0.10
    ?",↵
    -0.10
    POSITIVE LOGITS
     upp
    0.09
    ovah
    0.08
     mong
    0.08
     Dude
    0.08
     schle
    0.08
    ">#
    0.07
     pun
    0.07
     Holmes
    0.07
     Crist
    0.07
     заг
    0.07
    Activations Density 0.028%

    No Known Activations