© 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. 30546
    Prev
    Next
    INDEX
    Explanations

    main + [location/component noun]

    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
    hic
    -0.09
     anc
    -0.09
     backend
    -0.08
     appendix
    -0.08
     Appendix
    -0.08
     overlay
    -0.08
     mature
    -0.08
    overlay
    -0.08
     unf
    -0.07
     completion
    -0.07
    POSITIVE LOGITS
    /main
    0.16
    /Main
    0.14
    /big
    0.13
     body
    0.13
     part
    0.13
    mast
    0.13
    stem
    0.12
    (main
    0.12
     Body
    0.11
    .main
    0.11
    Activations Density 0.131%

    No Known Activations