© 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. 117592
    Prev
    Next
    INDEX
    Explanations

    girl

    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
    oning
    -0.08
     dolor
    -0.08
     orgas
    -0.07
     bapt
    -0.07
    inating
    -0.07
    adero
    -0.07
    abilidade
    -0.07
     erupt
    -0.07
    -navigation
    -0.07
     patented
    -0.07
    POSITIVE LOGITS
    们
    0.25
    -girl
    0.20
     whom
    0.18
    hood
    0.18
     young
    0.18
     who
    0.18
     girls
    0.17
     boys
    0.17
     male
    0.17
     males
    0.17
    Activations Density 0.076%

    No Known Activations