© 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. 31738
    Prev
    Next
    INDEX
    Explanations

    measurements (feet, meters, pounds)

    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
    [:]
    -0.08
     backstage
    -0.08
     compreh
    -0.08
     sui
    -0.08
    ters
    -0.08
    iga
    -0.08
     monumental
    -0.08
     di
    -0.08
    xFFFFFFFF
    -0.08
     birth
    -0.08
    POSITIVE LOGITS
    gor
    0.11
     solids
    0.10
    gren
    0.10
    ajs
    0.10
     correctly
    0.10
     bast
    0.10
    ITU
    0.10
    éĻ¢
    0.10
    unde
    0.10
     Temp
    0.10
    Activations Density 0.003%

    No Known Activations