© 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. 30015
    Prev
    Next
    INDEX
    Explanations

    hope this helps

    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
     hopefully
    -0.11
    hopefully
    -0.11
     Erd
    -0.10
    Hopefully
    -0.10
     Hopefully
    -0.09
     prom
    -0.09
     promises
    -0.09
    ahir
    -0.09
     gri
    -0.09
    uro
    -0.09
    POSITIVE LOGITS
     helpful
    0.16
     Helpful
    0.15
     Helps
    0.14
     helps
    0.13
     useful
    0.12
    help
    0.11
     helped
    0.10
     reply
    0.10
     clarified
    0.10
    iez
    0.10
    Activations Density 0.025%

    No Known Activations