© 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. 90567
    Prev
    Next
    INDEX
    Explanations

    heads, bodies, minds, hearts, selves

    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
    atee
    -0.09
     tricks
    -0.09
     Bre
    -0.08
     refs
    -0.08
     insults
    -0.08
    ern
    -0.08
    rip
    -0.08
    accordion
    -0.08
     corner
    -0.08
    uter
    -0.08
    POSITIVE LOGITS
     minds
    0.17
     mouths
    0.17
     bodies
    0.16
     heads
    0.16
     Heads
    0.16
     Minds
    0.16
     Bodies
    0.16
     tongues
    0.15
     hearts
    0.15
     selves
    0.14
    Activations Density 0.063%

    No Known Activations