© 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. 14242
    Prev
    Next
    INDEX
    Explanations

    access

    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
    Not in Any Lists

    No Comments

    Negative Logits
    chen
    -0.11
    apple
    -0.10
    lets
    -0.10
    ansen
    -0.09
    ass
    -0.09
    zsche
    -0.09
    ernels
    -0.09
    pone
    -0.09
    amic
    -0.09
    lette
    -0.09
    POSITIVE LOGITS
    ibly
    0.23
    ible
    0.21
    ory
    0.18
    ories
    0.17
    ibility
    0.17
    ibilit
    0.17
    ions
    0.17
    orial
    0.16
    ibil
    0.16
     Denied
    0.16
    Activations Density 0.073%

    No Known Activations