© 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. 117610
    Prev
    Next
    INDEX
    Explanations

    no action or development

    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
     uniquely
    -0.10
    DN
    -0.08
     imper
    -0.08
    bern
    -0.08
     empowering
    -0.08
     Nem
    -0.08
     Hale
    -0.07
     shin
    -0.07
    206
    -0.07
     Band
    -0.07
    POSITIVE LOGITS
     further
    0.14
     action
    0.14
     Further
    0.12
     nada
    0.12
     develops
    0.12
     nothing
    0.12
     happen
    0.12
     develop
    0.12
     between
    0.12
     ACTION
    0.11
    Activations Density 0.021%

    No Known Activations