© 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. 32922
    Prev
    Next
    INDEX
    Explanations

    seasons

    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
    strap
    -0.09
    件
    -0.09
     cork
    -0.08
    ominator
    -0.07
     chocol
    -0.07
    ios
    -0.07
     inde
    -0.07
    ahoma
    -0.07
     homer
    -0.07
     frequ
    -0.07
    POSITIVE LOGITS
     season
    0.23
    -season
    0.20
     Season
    0.19
     seasons
    0.18
     seasonal
    0.17
    Season
    0.16
    semester
    0.15
    season
    0.15
     festival
    0.15
     Festival
    0.14
    Activations Density 0.143%

    No Known Activations