© 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. 3375
    Prev
    Next
    INDEX
    Explanations

    pay for

    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
     Mug
    -0.11
    oping
    -0.11
    heads
    -0.11
    ropp
    -0.11
     Alley
    -0.10
     Payne
    -0.10
     Bark
    -0.10
    alley
    -0.10
    erner
    -0.10
     pard
    -0.10
    POSITIVE LOGITS
     homage
    0.21
     attention
    0.20
     tribute
    0.18
     dearly
    0.17
    offs
    0.15
     dividends
    0.15
    back
    0.14
     respects
    0.14
     Attention
    0.14
    rolls
    0.14
    Activations Density 0.079%

    No Known Activations