© 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. 17867
    Prev
    Next
    INDEX
    Explanations

    in Irish

    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
    kle
    -0.10
    Tumblr
    -0.09
    esk
    -0.08
     WikiLeaks
    -0.08
    kp
    -0.08
    esan
    -0.08
     Thornton
    -0.08
    .just
    -0.08
    yne
    -0.08
     kle
    -0.08
    POSITIVE LOGITS
    ’
    0.10
    haft
    0.10
    ÂĴ
    0.10
    -cut
    0.09
     sill
    0.09
     Hil
    0.09
     endlessly
    0.09
     necessarily
    0.09
    ucket
    0.09
     Hale
    0.09
    Activations Density 0.002%

    No Known Activations