© 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. 113555
    Prev
    Next
    INDEX
    Explanations

    phrases ending in 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
     divul
    -0.09
    ³³
    -0.08
    ocol
    -0.08
     wholly
    -0.08
     Kee
    -0.08
     doesnt
    -0.08
     ought
    -0.08
     UK
    -0.08
     kot
    -0.08
     swath
    -0.08
    POSITIVE LOGITS
    anko
    0.12
    FY
    0.12
     yay
    0.10
    UNIT
    0.10
    stor
    0.10
    breaking
    0.10
    /GL
    0.10
    oooooooo
    0.10
    AK
    0.10
     Semi
    0.10
    Activations Density 0.006%

    No Known Activations