© 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. 91361
    Prev
    Next
    INDEX
    Explanations

    work and related words

    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
     works
    -0.13
     Works
    -0.11
     workplace
    -0.11
     working
    -0.11
    Works
    -0.10
     tack
    -0.10
     Workplace
    -0.09
     ÑĢабоÑĤÑĭ
    -0.09
     Working
    -0.09
    ìŀij
    -0.09
    POSITIVE LOGITS
    aday
    0.25
    loads
    0.24
    manship
    0.23
    stations
    0.23
    bench
    0.22
     ethic
    0.22
    horse
    0.21
    spaces
    0.21
    shopping
    0.18
    day
    0.17
    Activations Density 0.315%

    No Known Activations