© 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. 15358
    Prev
    Next
    INDEX
    Explanations

    relaxing and sitting positions

    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
     dw
    -0.12
     Jag
    -0.12
    -org
    -0.12
    strup
    -0.12
     bast
    -0.11
     stamps
    -0.11
     Moments
    -0.11
    FW
    -0.11
     cheat
    -0.11
     corrid
    -0.11
    POSITIVE LOGITS
     prospective
    0.09
     relax
    0.09
     seat
    0.08
     relaxation
    0.08
     comfortably
    0.08
     firmly
    0.08
    576
    0.07
     popcorn
    0.07
     tight
    0.07
    Seat
    0.07
    Activations Density 0.006%

    No Known Activations