© 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. 88860
    Prev
    Next
    INDEX
    Explanations

    ac, af, av

    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
    ophage
    -0.10
    agers
    -0.09
    edom
    -0.09
    ìĸ´
    -0.09
    ager
    -0.09
    placement
    -0.09
    ocrates
    -0.09
    acular
    -0.08
    icle
    -0.08
    itzer
    -0.08
    POSITIVE LOGITS
    âĤ¬âĦ¢
    0.11
    epam
    0.10
     infinite
    0.10
     Damen
    0.10
    lı
    0.10
    ın
    0.09
     Infinite
    0.09
    TION
    0.09
    frica
    0.09
    à¥į
    0.09
    Activations Density 0.507%

    No Known Activations