© 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. 114686
    Prev
    Next
    INDEX
    Explanations

    sentence structure or punctuation

    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
     nudity
    -0.10
    ets
    -0.10
     clothes
    -0.10
     flirt
    -0.09
     wore
    -0.09
     wink
    -0.09
     flirting
    -0.09
     Clothes
    -0.09
     Glas
    -0.09
    izo
    -0.09
    POSITIVE LOGITS
     slowly
    0.12
     rhythm
    0.11
     rhyth
    0.10
     steadily
    0.10
     fren
    0.10
     deeply
    0.10
     suf
    0.10
     spat
    0.10
    dddd
    0.10
     repet
    0.10
    Activations Density 0.001%

    No Known Activations