© 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. 7141
    Prev
    Next
    INDEX
    Explanations

    file extensions and code references

    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
    ripe
    -0.10
    andon
    -0.10
     Mast
    -0.10
    mma
    -0.10
    edin
    -0.10
     Abbas
    -0.10
    apon
    -0.10
    ernel
    -0.10
    mast
    -0.09
     mast
    -0.09
    POSITIVE LOGITS
    html
    0.15
    .html
    0.12
     html
    0.11
    tml
    0.10
    php
    0.10
    htm
    0.09
    âĢ¦↵
    0.08
    âĢ¦↵↵
    0.08
     Html
    0.08
     php
    0.08
    Activations Density 0.067%

    No Known Activations