© 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. 48058
    Prev
    Next
    INDEX
    Explanations

    comparisons and intensifiers

    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
    isk
    -0.10
     ...↵↵↵↵
    -0.09
    urent
    -0.09
     Budd
    -0.09
     Sachs
    -0.09
     dr
    -0.09
    agate
    -0.09
    sv
    -0.09
    åIJ¦
    -0.09
    ULO
    -0.09
    POSITIVE LOGITS
     because
    0.12
     than
    0.12
     since
    0.11
    than
    0.10
     considering
    0.10
     due
    0.09
    -so
    0.09
    iona
    0.08
    because
    0.08
     if
    0.08
    Activations Density 0.024%

    No Known Activations