© 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. 48853
    Prev
    Next
    INDEX
    Explanations

    tourist attractions and destinations

    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
    work
    -0.10
    Boot
    -0.09
     newborn
    -0.09
    wall
    -0.09
     Boot
    -0.09
    nable
    -0.09
    stick
    -0.09
     reunited
    -0.08
     patched
    -0.08
    burn
    -0.08
    POSITIVE LOGITS
    y
    0.13
    -grade
    0.11
    -oriented
    0.11
    /pol
    0.11
     faint
    0.10
    -friendly
    0.10
     Attr
    0.10
     dollars
    0.10
    otel
    0.10
     influx
    0.10
    Activations Density 0.018%

    No Known Activations