© 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. 50884
    Prev
    Next
    INDEX
    Explanations

    Senegalese and Seneca words

    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
    IVA
    -0.09
    -sizing
    -0.09
     Zucker
    -0.09
    ottom
    -0.09
    ifie
    -0.09
    -bre
    -0.09
    ãĤº
    -0.09
    ź
    -0.09
    isers
    -0.09
    ennon
    -0.09
    POSITIVE LOGITS
    iors
    0.16
    eca
    0.16
    pai
    0.14
    ior
    0.14
    IOR
    0.13
    egal
    0.12
    ften
    0.11
     senator
    0.10
    ility
    0.10
    iore
    0.10
    Activations Density 0.075%

    No Known Activations