© 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. 48133
    Prev
    Next
    INDEX
    Explanations

    Union context

    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
    orny
    -0.10
    enco
    -0.09
    nap
    -0.09
     Garrison
    -0.09
    serie
    -0.08
    eler
    -0.08
    aton
    -0.08
    inate
    -0.08
    rag
    -0.08
    iete
    -0.08
    POSITIVE LOGITS
    oft
    0.12
    /div
    0.12
    /connection
    0.12
    emann
    0.11
    ugar
    0.10
    /part
    0.10
    /release
    0.10
     forged
    0.09
    Eb
    0.09
    aire
    0.09
    Activations Density 0.070%

    No Known Activations