© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112179
    Prev
    Next
    INDEX
    Explanations

    contracts, forms, files

    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
     yourself
    -0.17
     Yourself
    -0.14
     oneself
    -0.12
     yourselves
    -0.11
    azel
    -0.10
     Moody
    -0.10
     dispatch
    -0.10
     dex
    -0.10
     retarded
    -0.10
    oins
    -0.10
    POSITIVE LOGITS
     Burnett
    0.09
     Walton
    0.09
     Arn
    0.08
    vel
    0.08
     men
    0.08
     overt
    0.08
    ital
    0.08
    ä¼
    0.08
     submerged
    0.08
     woman
    0.08
    Activations Density 0.004%

    No Known Activations