© 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. 15530
    Prev
    Next
    INDEX
    Explanations

    dialogue openers

    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
    ..↵↵↵↵
    -0.11
    wid
    -0.11
    âĢ¦↵↵↵↵
    -0.10
    âĢ¦the
    -0.10
    fas
    -0.10
    [of
    -0.10
     Wid
    -0.10
     "---
    -0.10
    [assembly
    -0.10
    rier
    -0.10
    POSITIVE LOGITS
     hey
    0.22
     Hey
    0.21
    Hey
    0.20
     Wow
    0.18
     damn
    0.16
     wow
    0.16
     dude
    0.16
    hey
    0.16
     darn
    0.15
     Damn
    0.15
    Activations Density 0.026%

    No Known Activations