© 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. 114326
    Prev
    Next
    INDEX
    Explanations

    describing entities after a noun

    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
    onth
    -0.13
     upstairs
    -0.13
    AFE
    -0.12
    ogle
    -0.12
     downstairs
    -0.12
    otel
    -0.11
     Utf
    -0.11
     subsidi
    -0.11
    ittel
    -0.11
     unpl
    -0.10
    POSITIVE LOGITS
     whose
    0.13
     similar
    0.12
     roughly
    0.12
     identical
    0.11
     labeled
    0.11
     enc
    0.10
     resembling
    0.10
     labelled
    0.10
     surrounded
    0.10
     colored
    0.10
    Activations Density 0.235%

    No Known Activations