© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17822
    Prev
    Next
    INDEX
    Explanations

    call followed by another word

    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
    ede
    -0.09
    TM
    -0.08
    dbo
    -0.07
    .indexOf
    -0.07
     vis
    -0.07
    /crypto
    -0.07
    oj
    -0.07
     chests
    -0.07
    fax
    -0.07
     talking
    -0.07
    POSITIVE LOGITS
     bluff
    0.26
     attention
    0.25
    attention
    0.21
     Attention
    0.19
     shots
    0.17
     quits
    0.17
    Attention
    0.17
     Shots
    0.17
    igraphy
    0.16
    shots
    0.15
    Activations Density 0.200%

    No Known Activations