© 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. 91722
    Prev
    Next
    INDEX
    Explanations

    pleading questions or statements

    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
     unb
    -0.11
     Hind
    -0.10
     Gors
    -0.10
    fork
    -0.10
     lac
    -0.09
     commonplace
    -0.09
     tat
    -0.09
    (at
    -0.09
    .atom
    -0.08
    iel
    -0.08
    POSITIVE LOGITS
    BUM
    0.11
    erguson
    0.09
     Woj
    0.08
    572
    0.08
    GIN
    0.08
     kole
    0.08
    ACES
    0.08
     Steak
    0.08
    AZE
    0.08
    agra
    0.08
    Activations Density 0.099%

    No Known Activations