© 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. 27884
    Prev
    Next
    INDEX
    Explanations

    Apache License Version

    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
     Brief
    -0.08
     pal
    -0.08
     river
    -0.08
    rif
    -0.07
     pilgr
    -0.07
    Pel
    -0.07
     CZ
    -0.07
     Bav
    -0.07
     aug
    -0.07
    him
    -0.07
    POSITIVE LOGITS
     interchangeable
    0.12
    arin
    0.11
     degraded
    0.11
     Hess
    0.11
     gradual
    0.10
    enez
    0.10
     substitutes
    0.10
     dik
    0.10
    spy
    0.10
     Keller
    0.10
    Activations Density 0.001%

    No Known Activations