© 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. 14559
    Prev
    Next
    INDEX
    Explanations

    showy, extravagant, elaborate, spectacular

    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
     tidy
    -0.12
     cozy
    -0.10
    zone
    -0.10
     vibes
    -0.10
    elig
    -0.10
     petite
    -0.10
     BU
    -0.10
     Whip
    -0.10
     converse
    -0.10
     Joanna
    -0.09
    POSITIVE LOGITS
     extravagant
    0.23
     extravag
    0.22
     spectacle
    0.21
     flam
    0.20
     flair
    0.19
     elaborate
    0.17
     theatrical
    0.17
     spectacular
    0.17
     grand
    0.16
     excess
    0.16
    Activations Density 0.099%

    No Known Activations