© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91452
    Prev
    Next
    INDEX
    Explanations

    named characters as styles

    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
    boss
    -0.09
     Tess
    -0.08
    loy
    -0.08
    loader
    -0.08
     ()↵↵
    -0.08
    "',
    -0.08
     stall
    -0.08
     boss
    -0.08
    .Enum
    -0.08
     Huff
    -0.08
    POSITIVE LOGITS
    -esque
    0.18
    -style
    0.18
    -era
    0.15
    -type
    0.15
     notwithstanding
    0.14
     style
    0.14
    -types
    0.13
     ilk
    0.13
     fame
    0.13
    stype
    0.12
    Activations Density 0.239%

    No Known Activations