© 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. 117098
    Prev
    Next
    INDEX
    Explanations

    anatomy

    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
     statist
    -0.09
     flock
    -0.08
     coerc
    -0.08
     Kiss
    -0.08
     Fav
    -0.08
     compuls
    -0.08
     chron
    -0.07
     cocktails
    -0.07
     actionable
    -0.07
     infusion
    -0.07
    POSITIVE LOGITS
     anatom
    0.50
     anatomy
    0.50
     Anatomy
    0.45
     organs
    0.29
     dissect
    0.28
    atomy
    0.27
     physiology
    0.27
     diagrams
    0.27
     diagram
    0.26
     biology
    0.24
    Activations Density 0.740%

    No Known Activations