© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16733
    Prev
    Next
    INDEX
    Explanations

    phenomenon of, caused by, occurring

    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
     formidable
    -0.10
    bone
    -0.09
    entic
    -0.09
    uits
    -0.09
    ate
    -0.09
    brown
    -0.09
     fon
    -0.09
    ussions
    -0.09
    preneur
    -0.09
    Liv
    -0.09
    POSITIVE LOGITS
     phenomenon
    0.18
     phenomena
    0.18
     occurring
    0.16
     occurs
    0.13
     occur
    0.13
     occurred
    0.13
     occurrence
    0.13
    /problem
    0.11
     occurrences
    0.11
    ically
    0.11
    Activations Density 0.060%

    No Known Activations