© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115035
    Prev
    Next
    INDEX
    Explanations

    determine outcomes and matches

    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
    ACHE
    -0.10
     Successful
    -0.09
    uche
    -0.09
    æĶ
    -0.09
    agt
    -0.08
     scoop
    -0.08
     successful
    -0.08
     Parade
    -0.08
    akt
    -0.08
    .gnu
    -0.08
    POSITIVE LOGITS
     rematch
    0.14
     Determines
    0.13
     determining
    0.13
     determine
    0.12
     determines
    0.12
     comparing
    0.12
     judged
    0.12
     wager
    0.12
     duel
    0.12
     friendly
    0.11
    Activations Density 0.396%

    No Known Activations