© 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. 18378
    Prev
    Next
    INDEX
    Explanations

    language, motor control, cognition

    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
     Brain
    -0.13
    Brain
    -0.12
     brain
    -0.11
     minds
    -0.10
    brains
    -0.10
    omba
    -0.10
     RAW
    -0.10
     Mind
    -0.10
     harvest
    -0.10
     underground
    -0.09
    POSITIVE LOGITS
     sensation
    0.14
     emotions
    0.13
     motor
    0.13
     memories
    0.13
     consciousness
    0.12
     comprehension
    0.12
     perception
    0.12
     memory
    0.12
     speech
    0.12
     digestion
    0.12
    Activations Density 0.712%

    No Known Activations