© 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. 3754
    Prev
    Next
    INDEX
    Explanations

    .ht

    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
     garn
    -0.09
     Garn
    -0.09
    beg
    -0.09
    trees
    -0.08
     Garage
    -0.08
     finder
    -0.08
    _MISSING
    -0.08
     Sext
    -0.08
    ngle
    -0.08
     Beg
    -0.08
    POSITIVE LOGITS
    bourg
    0.10
    .pb
    0.10
    lieÃŁ
    0.10
    询
    0.09
    liest
    0.09
     Laud
    0.09
     relay
    0.09
    İ·
    0.09
     Fran
    0.09
     probable
    0.09
    Activations Density 0.020%

    No Known Activations