© 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. 32907
    Prev
    Next
    INDEX
    Explanations

    <script src

    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
     lyric
    -0.07
     chatt
    -0.07
    formats
    -0.07
     subtotal
    -0.07
    Translated
    -0.07
    izo
    -0.07
     enc
    -0.07
    wan
    -0.07
     viewers
    -0.07
    Mes
    -0.07
    POSITIVE LOGITS
     composer
    0.15
     compositions
    0.15
     compos
    0.14
     Composition
    0.14
     Composer
    0.14
     composing
    0.14
     compose
    0.14
     composition
    0.14
     dep
    0.14
    umd
    0.13
    Activations Density 1.963%

    No Known Activations