© 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. 6115
    Prev
    Next
    INDEX
    Explanations

    vice president, executive, science, communication

    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
    -hole
    -0.10
     @$
    -0.09
     apolog
    -0.09
     culture
    -0.09
     SPEED
    -0.09
    udeau
    -0.09
    anj
    -0.09
     Alive
    -0.09
     pedestrians
    -0.09
     Riding
    -0.09
    POSITIVE LOGITS
    unu
    0.10
     Eden
    0.10
     impatient
    0.10
     Naked
    0.10
     shim
    0.10
    alah
    0.10
     lie
    0.10
    uga
    0.09
    ousel
    0.09
     amet
    0.09
    Activations Density 0.025%

    No Known Activations