© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115904
    Prev
    Next
    INDEX
    Explanations

    operation, headquarters, overview

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Ging
    -0.08
     Pell
    -0.07
     toe
    -0.07
     flattering
    -0.07
     gauche
    -0.07
     goof
    -0.07
    coles
    -0.07
    ..
    -0.07
     billed
    -0.07
    peng
    -0.07
    POSITIVE LOGITS
    Escort
    0.15
     Escort
    0.13
     UNESCO
    0.13
     escort
    0.12
     prostitution
    0.12
     Azerbaijan
    0.11
     Tourism
    0.11
     INA
    0.11
     Belarus
    0.10
     vis
    0.10
    Activations Density 0.011%

    No Known Activations