© 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. 29721
    Prev
    Next
    INDEX
    Explanations

    character study

    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
     Breitbart
    -0.14
     ballo
    -0.12
     âĢķ
    -0.12
    resolver
    -0.11
     deleg
    -0.11
    .↵↵↵↵↵↵↵↵↵↵↵↵
    -0.11
     *,↵
    -0.10
     Unblock
    -0.10
     Pornhub
    -0.10
     Resolver
    -0.10
    POSITIVE LOGITS
     photographed
    0.12
     fotos
    0.12
     [...]
    0.12
     Photograph
    0.12
     photographer
    0.12
     Photography
    0.11
    Phot
    0.11
     ...
    0.11
     rainy
    0.11
     vintage
    0.11
    Activations Density 0.159%

    No Known Activations