© 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. 111602
    Prev
    Next
    INDEX
    Explanations

    need to, want to, suppose

    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
     ones
    -0.12
    cano
    -0.10
     ellas
    -0.10
    mdb
    -0.10
    ayo
    -0.10
     Lowell
    -0.10
    adol
    -0.09
     Tome
    -0.09
    util
    -0.09
    CLS
    -0.09
    POSITIVE LOGITS
     бÑĭÑĤÑĮ
    0.15
     that
    0.13
    that
    0.12
     avoir
    0.12
     having
    0.11
     be
    0.11
     being
    0.11
    zd
    0.10
     que
    0.10
     ÑĩÑĤо
    0.10
    Activations Density 0.291%

    No Known Activations