© 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. 25193
    Prev
    Next
    INDEX
    Explanations

    `.microsoft` links

    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
    igg
    -0.10
     âĢķ
    -0.09
     eng
    -0.09
    <|fim_middle|>
    -0.09
    �t
    -0.09
     Fine
    -0.09
     iam
    -0.08
    imary
    -0.08
     ÂŃ
    -0.08
     disgrace
    -0.08
    POSITIVE LOGITS
    Lng
    0.10
    inject
    0.10
     isOpen
    0.10
    [Int
    0.09
    safe
    0.09
     beiden
    0.09
    /cloud
    0.09
    integr
    0.09
     tengo
    0.09
    rez
    0.09
    Activations Density 0.005%

    No Known Activations