© 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. 33958
    Prev
    Next
    INDEX
    Explanations

    specialties and interests

    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
    ourn
    -0.09
     solution
    -0.09
     suff
    -0.09
     Solution
    -0.09
    Occurred
    -0.08
    Sink
    -0.08
    Literal
    -0.08
     SOLUTION
    -0.08
    Registers
    -0.08
     Suff
    -0.08
    POSITIVE LOGITS
     preferences
    0.18
     miscellaneous
    0.17
     hobbies
    0.16
     preferred
    0.16
     specialties
    0.16
     Languages
    0.15
    Languages
    0.15
     wishlist
    0.15
     languages
    0.15
     Preferences
    0.14
    Activations Density 0.097%

    No Known Activations