© 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. 5154
    Prev
    Next
    INDEX
    Explanations

    written by

    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
     Crash
    -0.10
     wr
    -0.09
     inse
    -0.09
    -l
    -0.08
     Clifford
    -0.08
    agged
    -0.08
    /TR
    -0.08
     truck
    -0.08
     Reyn
    -0.08
    378
    -0.08
    POSITIVE LOGITS
    written
    0.12
     Meer
    0.10
     assuming
    0.10
     written
    0.10
    -written
    0.09
     Conte
    0.09
     collabor
    0.09
    uras
    0.09
     consent
    0.09
    /cal
    0.09
    Activations Density 0.097%

    No Known Activations