© 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. 17457
    Prev
    Next
    INDEX
    Explanations

    advertisement links

    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
     Lets
    -0.12
    and
    -0.10
     cl
    -0.10
    Lets
    -0.10
     thats
    -0.10
    -dat
    -0.10
    instead
    -0.09
    another
    -0.09
     Noble
    -0.09
     slate
    -0.09
    POSITIVE LOGITS
    RELATED
    0.16
    advertisement
    0.14
    SEE
    0.14
    [image
    0.14
    ADVERTISEMENT
    0.13
    [js
    0.13
     Advertisement
    0.13
    MORE
    0.13
    "[
    0.12
     ![
    0.12
    Activations Density 0.175%

    No Known Activations