© 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. 8161
    Prev
    Next
    INDEX
    Explanations

    will + verb

    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
    unu
    -0.11
    Å¡ÃŃ
    -0.10
    ouv
    -0.10
     instantly
    -0.10
    rit
    -0.10
    aday
    -0.10
    beck
    -0.10
     agrees
    -0.10
    agree
    -0.10
    omba
    -0.09
    POSITIVE LOGITS
     dissect
    0.10
     enjoyment
    0.10
     exact
    0.10
     Sever
    0.10
    ogen
    0.09
     feast
    0.09
     Plum
    0.09
    -binary
    0.09
     tame
    0.09
     Mats
    0.09
    Activations Density 0.026%

    No Known Activations