© 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. 87703
    Prev
    Next
    INDEX
    Explanations

    skills and requirements

    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
    umba
    -0.12
    cott
    -0.11
     Richt
    -0.10
     Jes
    -0.10
     vex
    -0.10
     unint
    -0.10
     smear
    -0.09
     unbelievable
    -0.09
     Alic
    -0.09
     bathing
    -0.09
    POSITIVE LOGITS
     acquisition
    0.17
     acquired
    0.16
     skills
    0.15
     development
    0.14
    -building
    0.13
    Skills
    0.13
     Acquisition
    0.13
     Skills
    0.13
     possessed
    0.13
    -development
    0.12
    Activations Density 0.081%

    No Known Activations