© 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. 111995
    Prev
    Next
    INDEX
    Explanations

    body parts and health

    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
     stressing
    -0.10
    essler
    -0.09
     borne
    -0.08
     Stoke
    -0.08
    urf
    -0.08
     stroke
    -0.08
    glas
    -0.08
    utsch
    -0.08
    dm
    -0.08
    -headed
    -0.08
    POSITIVE LOGITS
     flank
    0.11
    utral
    0.10
    agate
    0.10
     Crosby
    0.10
    /org
    0.10
    funcs
    0.09
    lect
    0.09
    iances
    0.09
     Birch
    0.09
    :w
    0.09
    Activations Density 0.001%

    No Known Activations