© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5916
    Prev
    Next
    INDEX
    Explanations

    court circuit Chicago

    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
     reflex
    -0.10
    adients
    -0.10
     Lub
    -0.09
     separately
    -0.09
     Ecc
    -0.09
     grit
    -0.09
    BW
    -0.09
     BOT
    -0.09
     orgas
    -0.09
    rx
    -0.09
    POSITIVE LOGITS
     taller
    0.11
     intensified
    0.11
     hands
    0.11
     body
    0.11
     fuller
    0.10
     intens
    0.10
     tongues
    0.10
     kneeling
    0.10
     cords
    0.10
     Fil
    0.10
    Activations Density 0.014%

    No Known Activations