© 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. 33852
    Prev
    Next
    INDEX
    Explanations

    names and other specific nouns

    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
    however
    -0.08
     Budd
    -0.08
    cab
    -0.08
     duly
    -0.08
    etch
    -0.08
     therefore
    -0.08
     diver
    -0.08
     thus
    -0.08
     pe
    -0.07
     NOT
    -0.07
    POSITIVE LOGITS
     likewise
    0.17
    âĢ¦
    0.17
     simply
    0.17
     dit
    0.16
     outright
    0.15
    âĢ¦I
    0.15
    dit
    0.15
    ...
    0.15
     similarly
    0.14
    ,âĢ¦
    0.14
    Activations Density 0.205%

    No Known Activations