© 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. 111628
    Prev
    Next
    INDEX
    Explanations

    one day/week/night

    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
     immediate
    -0.09
    cco
    -0.08
     Wheeler
    -0.08
    forge
    -0.08
     Cause
    -0.08
     Paste
    -0.08
    atching
    -0.08
    FINITE
    -0.08
     Immediate
    -0.08
    \\\\
    -0.08
    POSITIVE LOGITS
     affair
    0.12
     stand
    0.12
    ers
    0.11
    er
    0.10
     Pee
    0.10
    endo
    0.10
     acquaintance
    0.10
    aneous
    0.10
    ìŀ
    0.10
     meaningless
    0.10
    Activations Density 0.002%

    No Known Activations