© 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. 24980
    Prev
    Next
    INDEX
    Explanations

    I hope

    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
     unaware
    -0.14
     recognizes
    -0.11
     noticing
    -0.11
     understandable
    -0.10
     unnoticed
    -0.10
     notice
    -0.10
     noticed
    -0.10
    Mage
    -0.10
     recognizable
    -0.10
     notices
    -0.10
    POSITIVE LOGITS
     accordingly
    0.12
    isque
    0.10
     wastes
    0.09
     nonetheless
    0.08
     Calder
    0.08
     ì¶
    0.08
    iza
    0.08
    hint
    0.08
    lr
    0.08
     also
    0.08
    Activations Density 0.276%

    No Known Activations