© 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. 113338
    Prev
    Next
    INDEX
    Explanations

    interjections and hesitations such as uh oh

    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
    eling
    -0.09
    elyn
    -0.08
    bron
    -0.08
    umph
    -0.08
     WTF
    -0.08
     Brace
    -0.07
    comb
    -0.07
     friendly
    -0.07
    bil
    -0.07
    clin
    -0.07
    POSITIVE LOGITS
     ance
    0.11
    gra
    0.11
    gnore
    0.11
    umer
    0.10
     OTHERWISE
    0.10
    [".
    0.10
    /tiny
    0.10
     WRONG
    0.10
    eric
    0.10
     buz
    0.10
    Activations Density 0.001%

    No Known Activations