© 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. 26806
    Prev
    Next
    INDEX
    Explanations

    off- side, season, ramps, target

    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
    alo
    -0.10
    alg
    -0.09
    aira
    -0.09
     dein
    -0.08
     Welch
    -0.08
    uesta
    -0.08
    wargs
    -0.08
    masters
    -0.08
    alive
    -0.07
    alah
    -0.07
    POSITIVE LOGITS
     offending
    0.10
     chance
    0.10
     chill
    0.09
     SIDE
    0.09
    -brand
    0.09
    ilter
    0.09
    lda
    0.09
     procure
    0.09
     assim
    0.09
    mes
    0.09
    Activations Density 0.010%

    No Known Activations