© 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. 112013
    Prev
    Next
    INDEX
    Explanations

    fight title championship

    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
     pari
    -0.10
     NFL
    -0.10
    onet
    -0.10
     dies
    -0.10
     pars
    -0.09
     unread
    -0.09
     comma
    -0.09
     Initial
    -0.09
     tempor
    -0.09
     readability
    -0.09
    POSITIVE LOGITS
     interfering
    0.13
     rematch
    0.12
     feud
    0.12
     tonight
    0.12
     interference
    0.12
     reinst
    0.12
     storyline
    0.12
     interfer
    0.11
     title
    0.11
     ally
    0.10
    Activations Density 0.284%

    No Known Activations