© 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. 29155
    Prev
    Next
    INDEX
    Explanations

    large amounts

    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
     happier
    -0.13
     safer
    -0.11
     simpler
    -0.11
     identical
    -0.10
     NEVER
    -0.10
     inadvert
    -0.10
     inadvertently
    -0.10
     merely
    -0.10
    ngr
    -0.09
     somehow
    -0.09
    POSITIVE LOGITS
     extensive
    0.36
     heavily
    0.33
     extensively
    0.32
     large
    0.32
     substantial
    0.30
     strong
    0.30
     plentiful
    0.30
     ample
    0.29
     considerable
    0.28
     sizable
    0.28
    Activations Density 1.964%

    No Known Activations