© 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. 7742
    Prev
    Next
    INDEX
    Explanations

    scheduled to be

    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
    ago
    -0.11
    DONE
    -0.11
     lasted
    -0.10
    QUIT
    -0.09
     Lit
    -0.09
     Kitt
    -0.09
     victories
    -0.08
    igue
    -0.08
    osc
    -0.08
     behaved
    -0.08
    POSITIVE LOGITS
     scheduled
    0.28
     Scheduled
    0.22
     expected
    0.21
    scheduled
    0.21
     slated
    0.20
    cheduled
    0.20
     planned
    0.20
    Scheduled
    0.18
     Expected
    0.18
     supposed
    0.18
    Activations Density 0.178%

    No Known Activations