© 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. 15943
    Prev
    Next
    INDEX
    Explanations

    special characters and code delimiters

    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
    /of
    -0.12
     Sink
    -0.10
    ÂĢÂĻ
    -0.10
    ï¸
    -0.10
    Jvm
    -0.10
    GetString
    -0.10
     __________________↵↵
    -0.10
    JNI
    -0.09
    FXML
    -0.09
     \↵
    -0.09
    POSITIVE LOGITS
    <table
    0.10
     ![
    0.10
    The
    0.09
     pur
    0.08
    There
    0.07
     The
    0.07
    urer
    0.07
    CHAPTER
    0.07
    ................................................................
    0.07
    ---
    0.07
    Activations Density 0.864%

    No Known Activations