© 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. 30763
    Prev
    Next
    INDEX
    Explanations

    numbers following "and"

    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
     Hague
    -0.10
    adel
    -0.09
     dès
    -0.09
    stdout
    -0.09
    orean
    -0.09
    ìķ
    -0.09
    yre
    -0.09
    .which
    -0.09
    hw
    -0.09
    erner
    -0.09
    POSITIVE LOGITS
     one
    0.24
     two
    0.23
     countless
    0.22
     numerous
    0.21
     three
    0.19
     four
    0.19
     dozens
    0.19
    two
    0.18
     five
    0.17
     six
    0.17
    Activations Density 0.557%

    No Known Activations