© 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. 91205
    Prev
    Next
    INDEX
    Explanations

    iacora / Miacora / MIA PaCa-2 / USuite / ihapate

    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
    /items
    -0.09
     mighty
    -0.09
    licht
    -0.09
    pez
    -0.09
    shipping
    -0.09
    chap
    -0.09
    /item
    -0.09
     easiest
    -0.09
    lined
    -0.09
    sto
    -0.08
    POSITIVE LOGITS
    ght
    0.11
    utenant
    0.11
    waukee
    0.11
    patrick
    0.10
    breaker
    0.10
    leness
    0.10
    oux
    0.10
    ernet
    0.10
    ellaneous
    0.10
    zelf
    0.09
    Activations Density 2.636%

    No Known Activations