© 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. 17745
    Prev
    Next
    INDEX
    Explanations

    file upload input

    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
     Jensen
    -0.10
     dist
    -0.09
     Twe
    -0.09
     Rescue
    -0.09
     Garrison
    -0.09
     collaps
    -0.09
     Helmet
    -0.09
    emie
    -0.09
     Norris
    -0.09
    iew
    -0.08
    POSITIVE LOGITS
     upload
    0.51
     uploading
    0.47
     uploads
    0.46
     Upload
    0.46
     uploaded
    0.44
    Upload
    0.40
    ä¸Ĭä¼ł
    0.39
     UPLOAD
    0.39
    upload
    0.39
    .upload
    0.36
    Activations Density 1.249%

    No Known Activations