© 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. 114500
    Prev
    Next
    INDEX
    Explanations

    There are

    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
     repl
    -0.10
     Dal
    -0.10
    lessly
    -0.09
     cad
    -0.09
    aps
    -0.09
     Crescent
    -0.09
     McL
    -0.09
     Dah
    -0.09
     Cad
    -0.09
     shar
    -0.09
    POSITIVE LOGITS
     involved
    0.17
     apl
    0.13
     lurking
    0.13
     available
    0.11
     gal
    0.10
     somewhere
    0.10
     looming
    0.09
     Gal
    0.09
    anh
    0.09
    avic
    0.09
    Activations Density 0.620%

    No Known Activations