© 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. 7339
    Prev
    Next
    INDEX
    Explanations

    check

    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
     split
    -0.08
     rim
    -0.07
     compensated
    -0.07
     Blanch
    -0.07
     inter
    -0.07
    -fed
    -0.07
    eb
    -0.07
     bore
    -0.06
    loom
    -0.06
     lok
    -0.06
    POSITIVE LOGITS
    /nav
    0.12
     Lans
    0.11
     Brock
    0.11
     bureaucracy
    0.10
     Bert
    0.10
    aight
    0.10
    ahn
    0.10
     Pols
    0.10
     Rockefeller
    0.10
     inequality
    0.10
    Activations Density 0.224%

    No Known Activations