© 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. 28820
    Prev
    Next
    INDEX
    Explanations

    interjections and filler words

    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
     extrem
    -0.08
    QUE
    -0.07
     Powered
    -0.07
    ardu
    -0.07
    hap
    -0.07
     driven
    -0.07
    vero
    -0.07
    380
    -0.07
    iders
    -0.07
    axis
    -0.07
    POSITIVE LOGITS
     uh
    0.19
     um
    0.18
     quote
    0.14
     gulp
    0.14
     well
    0.14
    uh
    0.13
     wow
    0.13
     hmm
    0.13
     ah
    0.12
     hey
    0.12
    Activations Density 0.020%

    No Known Activations