© 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. 92558
    Prev
    Next
    INDEX
    Explanations

    contextualized details and lists

    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
     prin
    -0.08
     woes
    -0.08
     visiting
    -0.08
    edia
    -0.08
     WH
    -0.08
    STA
    -0.08
    naire
    -0.08
    iren
    -0.08
     Kr
    -0.08
     again
    -0.08
    POSITIVE LOGITS
     she
    0.11
    she
    0.11
     I
    0.11
     adrenaline
    0.11
    -floating
    0.11
     reflex
    0.11
    he
    0.11
    due
    0.11
    She
    0.10
    arme
    0.10
    Activations Density 0.001%

    No Known Activations