© 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. 88900
    Prev
    Next
    INDEX
    Explanations

    I knew, you'd, we take

    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
     Harris
    -0.11
     Lars
    -0.10
    969
    -0.10
    ese
    -0.09
     synthetic
    -0.08
    zt
    -0.08
     gains
    -0.08
     modulus
    -0.08
     Tucker
    -0.08
    geber
    -0.08
    POSITIVE LOGITS
     aspire
    0.12
     duel
    0.10
     Duel
    0.10
     Lange
    0.10
     dealt
    0.10
     Conc
    0.10
     stumbled
    0.09
     jugg
    0.09
     Grave
    0.09
    ched
    0.09
    Activations Density 0.049%

    No Known Activations