© 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. 114587
    Prev
    Next
    INDEX
    Explanations

    apology or annoyance

    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
     mas
    -0.09
    Mas
    -0.09
    ason
    -0.09
     precaution
    -0.09
     Arch
    -0.08
    dire
    -0.08
    aku
    -0.08
    arch
    -0.08
     loft
    -0.08
     Blick
    -0.08
    POSITIVE LOGITS
     pest
    0.36
     annoying
    0.35
     annoy
    0.34
     nag
    0.33
     nuisance
    0.32
     bothering
    0.32
     bothers
    0.29
     anno
    0.27
     annoyance
    0.27
     bother
    0.26
    Activations Density 0.236%

    No Known Activations