© 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. 92516
    Prev
    Next
    INDEX
    Explanations

    ease of

    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
    ryo
    -0.12
    ÑĤе
    -0.11
    tery
    -0.11
    tes
    -0.10
    hei
    -0.10
    thesis
    -0.10
    shaw
    -0.09
    thal
    -0.09
     hei
    -0.09
    -esque
    -0.09
    POSITIVE LOGITS
    ful
    0.14
    -off
    0.12
    ably
    0.11
    -of
    0.10
    lessly
    0.10
     restrictions
    0.10
    hist
    0.10
    InOut
    0.10
     frankly
    0.10
    -flow
    0.10
    Activations Density 0.006%

    No Known Activations