© 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. 113037
    Prev
    Next
    INDEX
    Explanations

    things are

    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
    ylan
    -0.09
     interviewed
    -0.09
     elected
    -0.09
     Rates
    -0.09
     dab
    -0.09
     invited
    -0.09
    igne
    -0.08
     bored
    -0.08
     fores
    -0.08
     pomoc
    -0.08
    POSITIVE LOGITS
     bleak
    0.16
     unchanged
    0.13
     stressful
    0.13
     settled
    0.13
     tense
    0.12
     hectic
    0.12
     simpler
    0.12
     arranged
    0.12
     dire
    0.12
     tumult
    0.12
    Activations Density 0.046%

    No Known Activations