© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114590
    Prev
    Next
    INDEX
    Explanations

    html line breaks

    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
    adesh
    -0.11
     scrap
    -0.10
     Cotton
    -0.10
     Karn
    -0.09
    ibaba
    -0.09
     Crosby
    -0.09
    /access
    -0.09
    cpt
    -0.09
     ing
    -0.09
    icht
    -0.09
    POSITIVE LOGITS
    /tab
    0.10
    ajas
    0.10
    otal
    0.09
    ffi
    0.09
    FORCE
    0.09
    á»ĩn
    0.09
    force
    0.09
     shave
    0.08
     Coron
    0.08
    Duplicates
    0.08
    Activations Density 0.034%

    No Known Activations