© 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. 111511
    Prev
    Next
    INDEX
    Explanations

    people working or performing actions

    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
     Grü
    -0.09
     dece
    -0.09
    éĻ
    -0.09
     Winds
    -0.09
     Surre
    -0.09
     backing
    -0.09
     Gab
    -0.08
    omba
    -0.08
    arness
    -0.08
    ass
    -0.08
    POSITIVE LOGITS
     palms
    0.14
     palm
    0.14
     hands
    0.13
     fingertips
    0.13
     fingers
    0.13
     nonexistent
    0.13
     fists
    0.12
     finger
    0.12
     Gloves
    0.12
     fist
    0.12
    Activations Density 0.039%

    No Known Activations