© 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. 32197
    Prev
    Next
    INDEX
    Explanations

    periods of rest and time off

    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
     _$
    -0.10
     superf
    -0.08
    869
    -0.08
     mét
    -0.08
    esser
    -0.08
     aconte
    -0.08
    aira
    -0.08
     Grain
    -0.08
    ffd
    -0.08
     gran
    -0.08
    POSITIVE LOGITS
     periods
    0.19
     period
    0.17
    -period
    0.16
     durations
    0.13
    æľŁ
    0.12
    period
    0.12
     duration
    0.12
     allotted
    0.12
     Period
    0.12
    éĸĵ
    0.11
    Activations Density 0.171%

    No Known Activations