© 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. 113007
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical ranges

    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
     Hass
    -0.11
    /im
    -0.10
     Kaw
    -0.10
    eka
    -0.10
    lama
    -0.10
     Perez
    -0.10
    utral
    -0.10
    ecurity
    -0.10
    /re
    -0.10
     reim
    -0.10
    POSITIVE LOGITS
     depending
    0.17
     tops
    0.13
    depending
    0.13
     Depending
    0.11
     range
    0.10
    ish
    0.10
     timeframe
    0.09
    /etc
    0.08
     fram
    0.08
    lek
    0.08
    Activations Density 0.147%

    No Known Activations