© 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. 87597
    Prev
    Next
    INDEX
    Explanations

    body parts and their relation

    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
    rs
    -0.11
     morph
    -0.11
     thicker
    -0.10
     rs
    -0.10
     residual
    -0.10
     Benson
    -0.09
    esen
    -0.09
     Hull
    -0.09
     exit
    -0.09
    morph
    -0.09
    POSITIVE LOGITS
     effectively
    0.14
     Fah
    0.11
     Gon
    0.09
     Effect
    0.09
     Gir
    0.09
     creating
    0.09
     OPEN
    0.09
     Canter
    0.09
     conven
    0.09
    040
    0.09
    Activations Density 0.016%

    No Known Activations