© 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. 27595
    Prev
    Next
    INDEX
    Explanations

    yay, hooray, cheers

    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
    arella
    -0.12
    rog
    -0.12
     VERY
    -0.12
     Lust
    -0.11
     REALLY
    -0.11
     MISSING
    -0.11
     pleas
    -0.11
    apper
    -0.11
     Chill
    -0.11
     [|
    -0.11
    POSITIVE LOGITS
     yay
    0.16
     victory
    0.14
     onward
    0.13
     teamwork
    0.12
     team
    0.12
     cheering
    0.12
     TEAM
    0.12
     cheers
    0.11
     cheered
    0.11
     trium
    0.10
    Activations Density 0.058%

    No Known Activations