© 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. 28282
    Prev
    Next
    INDEX
    Explanations

    quilt, felt, slate, flannel

    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
     balloon
    -0.10
     Pik
    -0.10
     desert
    -0.09
     inflate
    -0.09
    /container
    -0.09
     oasis
    -0.09
     glitter
    -0.09
     sculpt
    -0.09
    usz
    -0.09
     Orlando
    -0.09
    POSITIVE LOGITS
     lumber
    0.13
     whiskey
    0.12
     shirt
    0.11
     Scottish
    0.11
     Scots
    0.10
     Canadian
    0.10
     Scotch
    0.10
     shirts
    0.10
    wood
    0.10
     wood
    0.10
    Activations Density 0.002%

    No Known Activations