© 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. 115464
    Prev
    Next
    INDEX
    Explanations

    wardrobe, closet, dressingroom

    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
    apult
    -0.10
     overhead
    -0.09
     raft
    -0.09
     ceiling
    -0.09
     Ceiling
    -0.09
     Coch
    -0.09
     Shark
    -0.09
     conveniently
    -0.09
     LATIN
    -0.09
     Patel
    -0.09
    POSITIVE LOGITS
     drawers
    0.22
     drawer
    0.14
     dresser
    0.13
     tops
    0.12
     lingerie
    0.12
     top
    0.12
     Top
    0.12
     keys
    0.12
     jewellery
    0.11
     Keys
    0.11
    Activations Density 0.010%

    No Known Activations