© 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. 7103
    Prev
    Next
    INDEX
    Explanations

    lepidopteran, leprechaun, leeches, leprosy, levetiracetam, leaching

    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
    ès
    -0.10
    elles
    -0.10
    ou
    -0.10
    erville
    -0.09
    orce
    -0.09
    nap
    -0.09
    ɵ
    -0.09
    re
    -0.09
    renderer
    -0.09
    entes
    -0.09
    POSITIVE LOGITS
    vens
    0.14
    athers
    0.12
    aser
    0.12
    avy
    0.11
     le
    0.11
    eway
    0.11
    ction
    0.11
    wd
    0.11
    asers
    0.11
    etcode
    0.11
    Activations Density 0.029%

    No Known Activations