© 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. 47652
    Prev
    Next
    INDEX
    Explanations

    fighting and battling

    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
     exc
    -0.09
     Nie
    -0.09
     pec
    -0.09
    istor
    -0.09
    linger
    -0.08
     hottest
    -0.08
    hausen
    -0.08
     Full
    -0.08
    quisition
    -0.08
    atical
    -0.08
    POSITIVE LOGITS
     Fighting
    0.15
     battling
    0.15
     fighting
    0.14
     fights
    0.13
     Fight
    0.12
    combat
    0.12
     Wrest
    0.12
     Combat
    0.12
     temptation
    0.11
    uye
    0.11
    Activations Density 0.023%

    No Known Activations