© 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. 92495
    Prev
    Next
    INDEX
    Explanations

    topic:

    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
     nominations
    -0.09
     bead
    -0.09
     ép
    -0.08
    .GenerationType
    -0.08
     togg
    -0.08
    éré
    -0.08
     listar
    -0.08
    zzo
    -0.08
     detail
    -0.08
    Expanded
    -0.08
    POSITIVE LOGITS
     stren
    0.09
     Cree
    0.09
     Ru
    0.09
    vari
    0.09
     ru
    0.08
    _cre
    0.08
     superf
    0.08
    ñ
    0.08
     exe
    0.08
     Lesson
    0.08
    Activations Density 0.041%

    No Known Activations