© 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. 30476
    Prev
    Next
    INDEX
    Explanations

    sitting, seat, cushion

    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
     dart
    -0.12
     shooting
    -0.11
     wound
    -0.09
     drip
    -0.09
     winding
    -0.09
     walking
    -0.09
     shot
    -0.09
     gunshot
    -0.09
    dart
    -0.09
     shoot
    -0.09
    POSITIVE LOGITS
     suff
    0.19
     cushion
    0.19
     fart
    0.17
     sitting
    0.16
     seat
    0.16
     smo
    0.16
     Sitting
    0.16
     cushions
    0.16
     Seat
    0.15
     sit
    0.15
    Activations Density 0.014%

    No Known Activations