© 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. 4837
    Prev
    Next
    INDEX
    Explanations

    Greek letters and math notation

    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
     rec
    -0.09
     bell
    -0.08
     JP
    -0.07
    pes
    -0.07
     blinking
    -0.07
     wre
    -0.07
     aka
    -0.07
    858
    -0.07
     magnet
    -0.06
     wink
    -0.06
    POSITIVE LOGITS
    mmm
    0.13
    agner
    0.13
    MMMM
    0.12
    MMM
    0.12
     Ist
    0.11
    .hh
    0.11
    :mm
    0.11
    neath
    0.11
    urry
    0.11
    ieee
    0.10
    Activations Density 0.003%

    No Known Activations