© 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. 17265
    Prev
    Next
    INDEX
    Explanations

    beds and sleeping arrangements

    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
     meas
    -0.09
     pix
    -0.09
    pol
    -0.09
     rally
    -0.09
     fract
    -0.09
    adan
    -0.09
     statistics
    -0.09
    enu
    -0.09
    neck
    -0.08
    ihu
    -0.08
    POSITIVE LOGITS
     bed
    0.48
     beds
    0.47
     Beds
    0.35
    bed
    0.34
    -bed
    0.34
     Bed
    0.32
     BED
    0.30
    BED
    0.29
     bunk
    0.28
    Bed
    0.28
    Activations Density 0.192%

    No Known Activations