© 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. 112903
    Prev
    Next
    INDEX
    Explanations

    clothing 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
     Bron
    -0.11
     rejo
    -0.10
    ilos
    -0.10
    AO
    -0.10
     catapult
    -0.10
     unpack
    -0.10
    robots
    -0.10
     dipping
    -0.10
    rote
    -0.10
    isma
    -0.10
    POSITIVE LOGITS
     coat
    0.21
     coats
    0.18
     Coat
    0.17
    coat
    0.17
     jacket
    0.15
     Jacket
    0.14
     shoes
    0.13
     hat
    0.11
     jackets
    0.10
     Shoes
    0.10
    Activations Density 0.042%

    No Known Activations