© 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. 6902
    Prev
    Next
    INDEX
    Explanations

    effective dates and starting times

    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
     repeatedly
    -0.10
     delaying
    -0.10
     before
    -0.09
    och
    -0.09
    before
    -0.09
     McB
    -0.09
     Trot
    -0.09
     Before
    -0.09
    _before
    -0.09
    urs
    -0.09
    POSITIVE LOGITS
     starting
    0.28
     Starting
    0.25
    starting
    0.24
    Starting
    0.23
     onwards
    0.22
     beginning
    0.22
     thereafter
    0.19
     onward
    0.19
     Beginning
    0.18
     effective
    0.18
    Activations Density 0.685%

    No Known Activations