© 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. 115901
    Prev
    Next
    INDEX
    Explanations

    thrown or blasted

    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
     Heath
    -0.10
     Daly
    -0.09
    prd
    -0.09
    agar
    -0.09
    ilog
    -0.09
    heed
    -0.08
    furt
    -0.08
     Jur
    -0.08
     incent
    -0.08
    eper
    -0.08
    POSITIVE LOGITS
     thrown
    0.20
     tossed
    0.20
     tumble
    0.18
     toss
    0.18
     slammed
    0.18
     slamming
    0.18
     slam
    0.17
    Thrown
    0.16
     tossing
    0.15
     pinned
    0.15
    Activations Density 0.126%

    No Known Activations