© 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. 29483
    Prev
    Next
    INDEX
    Explanations

    Options, License, none

    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
     cork
    -0.10
     mash
    -0.10
     Mash
    -0.10
     Cork
    -0.10
    imb
    -0.10
     Toro
    -0.09
    iddy
    -0.09
     Patri
    -0.09
    eros
    -0.09
     Cinder
    -0.09
    POSITIVE LOGITS
    etus
    0.12
     homosex
    0.09
    SENS
    0.09
     Leh
    0.09
     terme
    0.09
     Devils
    0.09
     Holl
    0.09
     Alv
    0.09
     STATS
    0.09
     Eck
    0.08
    Activations Density 0.005%

    No Known Activations