© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32302
    Prev
    Next
    INDEX
    Explanations

    guinea-pig

    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
     grinding
    -0.09
     Slo
    -0.08
     slo
    -0.08
     Berm
    -0.08
    orgia
    -0.08
     Orbit
    -0.08
     -------------------------------------------------------------------------
    -0.08
     Grinding
    -0.08
     Michaels
    -0.08
     daytime
    -0.08
    POSITIVE LOGITS
     goose
    0.12
     Goose
    0.11
    laden
    0.09
    \Id
    0.09
     Marathon
    0.09
    äch
    0.09
     sheds
    0.08
     mou
    0.08
    uthor
    0.08
     feathers
    0.08
    Activations Density 0.005%

    No Known Activations