© 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. 49949
    Prev
    Next
    INDEX
    Explanations

    file type suffixes

    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
     Jeg
    -0.09
    pany
    -0.09
     Ying
    -0.09
     Aw
    -0.08
    feb
    -0.08
     stakes
    -0.08
     Ary
    -0.08
    czy
    -0.08
    quest
    -0.08
     Ang
    -0.08
    POSITIVE LOGITS
    illo
    0.09
     Benson
    0.09
     Coast
    0.09
    cts
    0.09
     dri
    0.09
    nts
    0.09
    erk
    0.08
    CTS
    0.08
     halftime
    0.08
     hardest
    0.08
    Activations Density 0.001%

    No Known Activations