© 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. 30905
    Prev
    Next
    INDEX
    Explanations

    peak or maximum

    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
     restarted
    -0.10
     barely
    -0.08
     lower
    -0.08
     tolerate
    -0.08
     occasion
    -0.08
     soo
    -0.08
     perpetual
    -0.08
     longer
    -0.08
     Lower
    -0.08
     scant
    -0.08
    POSITIVE LOGITS
     peak
    0.73
     Peak
    0.59
     peaked
    0.58
    Peak
    0.57
    peak
    0.57
     peaks
    0.54
    _peak
    0.45
     Peaks
    0.41
    /Peak
    0.38
     maximum
    0.32
    Activations Density 0.896%

    No Known Activations