© 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. 90013
    Prev
    Next
    INDEX
    Explanations

    punctuation indicating end of phrase

    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
    ...↵
    -0.15
    ...↵↵↵
    -0.15
    ...↵↵
    -0.14
    :↵↵↵
    -0.13
    ...↵↵↵↵
    -0.13
     ("
    -0.12
     "...
    -0.12
     :↵↵
    -0.12
    ..↵
    -0.11
     :↵↵↵↵
    -0.11
    POSITIVE LOGITS
     [
    0.25
    ,”
    0.25
    ,"
    0.24
     [...]
    0.21
    .”↵↵
    0.21
     [âĢ¦]
    0.20
    ."↵↵
    0.20
    [s
    0.19
    [,]
    0.19
     ,"
    0.18
    Activations Density 0.223%

    No Known Activations