© 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. 29526
    Prev
    Next
    INDEX
    Explanations

    space

    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
     deps
    -0.08
    /sources
    -0.08
     SetValue
    -0.08
    nock
    -0.08
    steen
    -0.08
    jm
    -0.08
    Fallback
    -0.08
     slips
    -0.08
     excursion
    -0.08
     sortable
    -0.07
    POSITIVE LOGITS
     space
    0.29
    (space
    0.24
     Space
    0.24
    Space
    0.24
    space
    0.24
     SPACE
    0.23
    -space
    0.23
    .Space
    0.22
     spaces
    0.22
    .space
    0.22
    Activations Density 0.344%

    No Known Activations