© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 116793
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    iar
    -0.11
     rid
    -0.09
    riter
    -0.09
     sexes
    -0.09
     Ur
    -0.09
    aji
    -0.09
    ür
    -0.09
    ium
    -0.09
     Dahl
    -0.08
    æ°
    -0.08
    POSITIVE LOGITS
     unheard
    0.10
     cron
    0.10
     fellow
    0.10
    ebb
    0.10
     Those
    0.09
    afa
    0.09
    those
    0.09
     Instances
    0.09
     Guards
    0.09
     individually
    0.09
    Activations Density 0.012%

    No Known Activations