© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7966
    Prev
    Next
    INDEX
    Explanations

    gray or grey

    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
     redhead
    -0.11
     redd
    -0.10
     red
    -0.10
    kart
    -0.10
    yal
    -0.10
     yellow
    -0.10
    idis
    -0.09
    rollo
    -0.09
     Torch
    -0.09
    ibles
    -0.08
    POSITIVE LOGITS
    ish
    0.19
    hound
    0.17
    -green
    0.13
     grey
    0.13
    -scale
    0.13
    ed
    0.13
     Grey
    0.12
    son
    0.12
    don
    0.12
     gray
    0.12
    Activations Density 0.010%

    No Known Activations