© 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. 29478
    Prev
    Next
    INDEX
    Explanations

    confused 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
    Not in Any Lists

    No Comments

    Negative Logits
     routinely
    -0.11
    atab
    -0.10
     fools
    -0.09
    cken
    -0.09
    jest
    -0.09
    KER
    -0.09
     conscious
    -0.09
     Patterson
    -0.09
    oya
    -0.09
     Alvarez
    -0.09
    POSITIVE LOGITS
    /dis
    0.11
    /fr
    0.10
    ammo
    0.10
    ingly
    0.10
    imd
    0.09
    obel
    0.09
     mounting
    0.09
    /problems
    0.08
     why
    0.08
    /conf
    0.08
    Activations Density 0.008%

    No Known Activations