© 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. 116315
    Prev
    Next
    INDEX
    Explanations

    interruption while working

    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
     geg
    -0.10
    ereg
    -0.10
    ulton
    -0.09
    Postal
    -0.08
    cdn
    -0.08
    xr
    -0.08
     lÃŃ
    -0.08
     edged
    -0.08
    ider
    -0.08
    gle
    -0.08
    POSITIVE LOGITS
    æŃ£åľ¨
    0.30
     busy
    0.22
    busy
    0.20
     ongoing
    0.20
     finishing
    0.20
    Busy
    0.18
     Busy
    0.18
     interrupted
    0.17
    ongo
    0.17
     loung
    0.16
    Activations Density 0.261%

    No Known Activations