© 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. 26235
    Prev
    Next
    INDEX
    Explanations

    clothing items and accessories

    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
    REC
    -0.10
    umbed
    -0.10
     intact
    -0.10
     luk
    -0.10
    urv
    -0.10
     unfolding
    -0.09
    604
    -0.09
    -products
    -0.09
    æĸŃ
    -0.09
     Rever
    -0.09
    POSITIVE LOGITS
     borrowed
    0.13
     supplemented
    0.12
     accompanied
    0.11
     reminiscent
    0.11
     imported
    0.10
     accessor
    0.10
     topped
    0.10
     accompany
    0.10
     coupled
    0.09
     combo
    0.09
    Activations Density 0.051%

    No Known Activations