© 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. 17352
    Prev
    Next
    INDEX
    Explanations

    licenses this file

    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
     Shib
    -0.08
    ık
    -0.08
     GIVEN
    -0.08
     Kis
    -0.08
    corn
    -0.08
     plur
    -0.08
     Sever
    -0.08
     DIST
    -0.07
    ibri
    -0.07
    nof
    -0.07
    POSITIVE LOGITS
     grav
    0.11
     monet
    0.11
     Tit
    0.10
    uld
    0.10
     bil
    0.10
     punct
    0.10
    =end
    0.10
     dying
    0.09
    esk
    0.09
     politic
    0.09
    Activations Density 0.005%

    No Known Activations