© 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. 47379
    Prev
    Next
    INDEX
    Explanations

    date followed by âĢ¢

    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
     Rus
    -0.08
    .?
    -0.08
     pare
    -0.08
     Ange
    -0.08
    -aff
    -0.07
     Scot
    -0.07
     aff
    -0.07
     Cob
    -0.07
    ween
    -0.07
    ?s
    -0.07
    POSITIVE LOGITS
     âĢ¢
    0.17
    âĢ¢
    0.16
    âĢ¢↵↵
    0.14
    .âĢ¢
    0.12
     Gors
    0.11
     snatch
    0.11
    %i
    0.11
    à¹Į
    0.11
     blinded
    0.10
    laps
    0.10
    Activations Density 0.066%

    No Known Activations