© 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. 115628
    Prev
    Next
    INDEX
    Explanations

    scoring and results

    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
    iek
    -0.11
    rats
    -0.10
     recuper
    -0.10
    ->$
    -0.10
     Contributors
    -0.09
     contributed
    -0.09
    trap
    -0.09
     Trap
    -0.09
     slippery
    -0.09
    rig
    -0.09
    POSITIVE LOGITS
     touchdowns
    0.14
     points
    0.12
     tickets
    0.12
     touchdown
    0.10
     hits
    0.09
     against
    0.09
     chicks
    0.09
    /Register
    0.09
     victories
    0.09
     repeated
    0.09
    Activations Density 0.013%

    No Known Activations