© 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. 6292
    Prev
    Next
    INDEX
    Explanations

    long way to go

    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
     rebut
    -0.11
     Scha
    -0.10
    qd
    -0.10
     Strand
    -0.09
    odes
    -0.09
     herald
    -0.09
    qué
    -0.09
    iston
    -0.09
    roi
    -0.09
     Scenario
    -0.09
    POSITIVE LOGITS
     work
    0.23
     challenges
    0.17
    work
    0.16
     miles
    0.16
     room
    0.16
    Work
    0.16
     Work
    0.15
     uphill
    0.15
     much
    0.15
     Challenges
    0.15
    Activations Density 0.210%

    No Known Activations