© 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. 15402
    Prev
    Next
    INDEX
    Explanations

    practically every

    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
    neau
    -0.11
     utterly
    -0.10
    erk
    -0.10
     absolutely
    -0.10
    ilan
    -0.09
    eg
    -0.09
    most
    -0.09
    enz
    -0.09
    /actions
    -0.09
     apparently
    -0.09
    POSITIVE LOGITS
    ity
    0.14
     minded
    0.13
    -minded
    0.12
    bery
    0.09
    spy
    0.09
    -speaking
    0.09
     Genius
    0.09
    spe
    0.09
    ities
    0.09
     genius
    0.09
    Activations Density 0.006%

    No Known Activations