© 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. 7257
    Prev
    Next
    INDEX
    Explanations

    sports match dates

    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
    amba
    -0.12
     Feinstein
    -0.12
    Locker
    -0.12
    rama
    -0.12
    uddle
    -0.11
     pkt
    -0.11
     chim
    -0.11
     Guerrero
    -0.11
    ipa
    -0.11
    rale
    -0.11
    POSITIVE LOGITS
     matches
    0.18
     match
    0.17
     games
    0.15
     opener
    0.13
     Match
    0.13
     rematch
    0.12
     Matches
    0.12
     scheduled
    0.12
     decisive
    0.12
     showdown
    0.12
    Activations Density 3.304%

    No Known Activations