© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89771
    Prev
    Next
    INDEX
    Explanations

    place names after connectors

    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
     CBS
    -0.09
    Kansas
    -0.09
     Kansas
    -0.08
     Japanese
    -0.08
     Massachusetts
    -0.07
     NBC
    -0.07
     FDA
    -0.07
     Smithsonian
    -0.07
     Command
    -0.07
    CBS
    -0.07
    POSITIVE LOGITS
     dara
    0.11
     regional
    0.10
     Bale
    0.10
    /dr
    0.10
     recur
    0.09
    /play
    0.09
    å¼Ĥ
    0.09
     rushes
    0.09
     Regional
    0.09
     Hubb
    0.09
    Activations Density 1.951%

    No Known Activations