© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8315
    Prev
    Next
    INDEX
    Explanations

    no tickets, IDs, deposit, installation, glue, advertising, card, waitlists

    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
    Negative Logits
    296
    -0.10
    uce
    -0.10
    Adjusted
    -0.10
    tc
    -0.09
     lest
    -0.09
    urg
    -0.09
    thr
    -0.09
    anes
    -0.09
     Dad
    -0.09
     ACTIVE
    -0.09
    POSITIVE LOGITS
     hass
    0.21
     Hass
    0.18
     hassle
    0.16
     whatsoever
    0.10
     fees
    0.10
     overhead
    0.10
    olley
    0.09
    hev
    0.09
     mess
    0.09
    zas
    0.09
    Activations Density 0.055%

    No Known Activations