© 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. 112921
    Prev
    Next
    INDEX
    Explanations

    not included or listed

    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
    ucher
    -0.10
    xac
    -0.09
     anc
    -0.09
    acin
    -0.09
    arg
    -0.09
    omba
    -0.09
    hek
    -0.09
    hog
    -0.09
     Owen
    -0.09
     Garn
    -0.09
    POSITIVE LOGITS
     among
    0.36
     included
    0.35
     Included
    0.33
     amongst
    0.33
    among
    0.31
    included
    0.30
    Included
    0.29
     INCLUDED
    0.29
     listed
    0.27
     Among
    0.26
    Activations Density 0.836%

    No Known Activations