© 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. 33620
    Prev
    Next
    INDEX
    Explanations

    tossing around, turning over, distributed

    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
     grat
    -0.08
     cork
    -0.08
     diary
    -0.08
     Washer
    -0.08
     sec
    -0.08
     hairy
    -0.08
    guard
    -0.07
    bol
    -0.07
    ungan
    -0.07
     sealing
    -0.07
    POSITIVE LOGITS
     tossing
    0.13
     endlessly
    0.13
     restless
    0.12
     turnovers
    0.12
     toss
    0.12
    -turn
    0.12
     offs
    0.11
     repeatedly
    0.11
     frustr
    0.11
    turnstile
    0.11
    Activations Density 0.002%

    No Known Activations