© 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. 30845
    Prev
    Next
    INDEX
    Explanations

    Nova Scotia

    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
     Nolan
    -0.10
    ento
    -0.09
     rebound
    -0.09
    oon
    -0.09
    nos
    -0.09
    mek
    -0.08
     Sark
    -0.08
     explo
    -0.08
    bounce
    -0.08
    esk
    -0.08
    POSITIVE LOGITS
     ll
    0.10
     Arbor
    0.09
     Majority
    0.09
     drv
    0.09
    riel
    0.09
     diffs
    0.09
     ++↵
    0.09
     Schwarz
    0.09
     Pins
    0.09
     Highest
    0.09
    Activations Density 0.001%

    No Known Activations