© 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. 25445
    Prev
    Next
    INDEX
    Explanations

    now or next

    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
    isce
    -0.10
    gems
    -0.09
     willen
    -0.09
    maids
    -0.09
    agers
    -0.09
    owment
    -0.09
    Opaque
    -0.09
    Already
    -0.09
     Griffith
    -0.09
    yg
    -0.09
    POSITIVE LOGITS
     next
    0.23
     now
    0.20
     challenge
    0.19
     task
    0.19
    next
    0.18
     Now
    0.17
     hurdle
    0.17
    Next
    0.17
    now
    0.16
     Next
    0.16
    Activations Density 0.274%

    No Known Activations