© 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. 26883
    Prev
    Next
    INDEX
    Explanations

    dialogue opening 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
    —I
    -0.09
     we
    -0.09
     I
    -0.08
    elda
    -0.08
     panc
    -0.08
    opi
    -0.08
    flix
    -0.07
    kö
    -0.07
     Will
    -0.07
     there
    -0.07
    POSITIVE LOGITS
     Well
    0.21
    Well
    0.21
     Oh
    0.18
    Oh
    0.18
     well
    0.17
     Hmm
    0.17
    well
    0.17
     Hey
    0.16
     oh
    0.16
     WELL
    0.16
    Activations Density 0.067%

    No Known Activations