© 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. 8151
    Prev
    Next
    INDEX
    Explanations

    gagged or bound

    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
     brows
    -0.11
     eyebrows
    -0.11
     explic
    -0.11
    ycz
    -0.11
     stools
    -0.11
     defiance
    -0.10
    owe
    -0.10
     imagin
    -0.10
    browse
    -0.10
     poses
    -0.10
    POSITIVE LOGITS
     blind
    0.17
     Blind
    0.16
     covering
    0.16
     hood
    0.14
     gag
    0.14
     Cover
    0.13
     cover
    0.13
     covered
    0.13
     kidn
    0.12
     duct
    0.12
    Activations Density 0.076%

    No Known Activations