© 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. 90509
    Prev
    Next
    INDEX
    Explanations

    question marks or colons

    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
    Anyway
    -0.12
     Anyway
    -0.10
     anyways
    -0.10
     anyway
    -0.09
     Forgotten
    -0.09
    ipur
    -0.09
     unknow
    -0.08
     nevertheless
    -0.08
     weakened
    -0.08
    ois
    -0.08
    POSITIVE LOGITS
    Sounds
    0.17
     Amen
    0.15
     Sounds
    0.15
     sounds
    0.15
     OK
    0.15
     duly
    0.15
     THAT
    0.14
    Correction
    0.14
     That
    0.14
    sounds
    0.13
    Activations Density 0.043%

    No Known Activations