© 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. 49895
    Prev
    Next
    INDEX
    Explanations

    separate rooms, kitchens, fireplaces, pools

    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
     towels
    -0.11
     gloves
    -0.10
     envelopes
    -0.10
     Gloves
    -0.10
    ubic
    -0.10
     pillows
    -0.10
    intern
    -0.09
     towel
    -0.09
     cushions
    -0.09
     Boxes
    -0.09
    POSITIVE LOGITS
     fireplace
    0.14
     cooking
    0.12
     seperate
    0.12
     Separate
    0.12
     cooks
    0.11
     kitchen
    0.11
     Fireplace
    0.11
     separate
    0.11
     DJ
    0.11
     pool
    0.10
    Activations Density 0.132%

    No Known Activations