© 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. 111401
    Prev
    Next
    INDEX
    Explanations

    back followed by specific 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
     comed
    -0.11
    ifo
    -0.10
     ec
    -0.10
     Amen
    -0.10
    thers
    -0.10
     unfamiliar
    -0.09
    elp
    -0.09
    emaker
    -0.09
    ipo
    -0.09
     penny
    -0.09
    POSITIVE LOGITS
     Witt
    0.10
     discrete
    0.10
     ruin
    0.09
     cabel
    0.09
     discret
    0.09
     rollback
    0.09
     Hamm
    0.08
    hatt
    0.08
     safeguard
    0.08
     refund
    0.08
    Activations Density 0.002%

    No Known Activations