© 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. 4139
    Prev
    Next
    INDEX
    Explanations

    asking for clarification or opinions

    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
    Compare
    -0.13
    Comparison
    -0.13
     Comparison
    -0.12
     Compare
    -0.11
     comparison
    -0.11
     synthetic
    -0.10
     controvers
    -0.10
    ogi
    -0.10
     verdict
    -0.10
    Tips
    -0.10
    POSITIVE LOGITS
     questionnaire
    0.15
     gathering
    0.15
    éĹ®
    0.15
     probing
    0.15
     inquire
    0.15
     gather
    0.14
     assessing
    0.14
     understanding
    0.14
     asks
    0.14
     intake
    0.14
    Activations Density 0.315%

    No Known Activations