© 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. 14962
    Prev
    Next
    INDEX
    Explanations

    submit or surrendered

    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
    ainer
    -0.11
     Lik
    -0.11
     solicit
    -0.10
     solic
    -0.10
     Fuse
    -0.10
    jos
    -0.10
    ast
    -0.09
    OfType
    -0.09
    ahn
    -0.09
     Quad
    -0.09
    POSITIVE LOGITS
     authority
    0.11
     control
    0.11
     fully
    0.11
     unto
    0.10
    Authority
    0.09
    authority
    0.08
    emy
    0.08
     kepada
    0.08
    control
    0.08
    canf
    0.08
    Activations Density 0.006%

    No Known Activations