© 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. 50682
    Prev
    Next
    INDEX
    Explanations

    sequences like 'and' or punctuation followed by continuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     other
    -0.14
     otherwise
    -0.13
     broader
    -0.12
     Other
    -0.11
    Other
    -0.11
    Otherwise
    -0.11
    otherwise
    -0.11
     Otherwise
    -0.10
    other
    -0.09
     autres
    -0.09
    POSITIVE LOGITS
    Similarly
    0.22
     Similarly
    0.21
     similarly
    0.21
     Likewise
    0.19
     Dit
    0.18
     likewise
    0.18
    Lik
    0.17
     Repeat
    0.15
    lik
    0.15
    Repeat
    0.14
    Activations Density 0.350%

    No Known Activations