© 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. 26431
    Prev
    Next
    INDEX
    Explanations

    scaring, scours, scorch, scuttle

    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
    oyal
    -0.10
     Bowman
    -0.10
     tight
    -0.09
     Nes
    -0.09
    onis
    -0.09
    aken
    -0.09
    ader
    -0.09
    aders
    -0.08
    usiness
    -0.08
    elage
    -0.08
    POSITIVE LOGITS
     scramble
    0.11
    ritch
    0.10
    run
    0.10
    utt
    0.10
     ott
    0.10
    Wir
    0.10
    OTT
    0.10
    /mp
    0.10
    oured
    0.10
     scour
    0.10
    Activations Density 0.004%

    No Known Activations