© 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. 47323
    Prev
    Next
    INDEX
    Explanations

    EDINA and Archives with colons

    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
    bled
    -0.09
    acl
    -0.08
    utes
    -0.08
     Readers
    -0.08
     Commit
    -0.08
     commit
    -0.08
    omy
    -0.08
     theoretical
    -0.08
     Stevens
    -0.08
     heights
    -0.08
    POSITIVE LOGITS
     dysfunction
    0.12
     medication
    0.12
     medications
    0.12
     drugs
    0.11
    /fr
    0.11
     pills
    0.11
     frontier
    0.11
    ema
    0.11
    ibles
    0.10
     Dysfunction
    0.10
    Activations Density 0.011%

    No Known Activations