© 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. 114566
    Prev
    Next
    INDEX
    Explanations

    continuing onward, subsequent actions

    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
     returning
    -0.15
    Returning
    -0.15
     Returning
    -0.15
    itar
    -0.12
     returns
    -0.12
     retreated
    -0.11
     returned
    -0.11
     return
    -0.11
     retreat
    -0.11
    (return
    -0.10
    POSITIVE LOGITS
     onward
    0.21
     onwards
    0.19
     crossing
    0.18
     crossed
    0.15
     continuation
    0.14
     Crossing
    0.14
     crosses
    0.13
     continuing
    0.12
     skirt
    0.12
     continue
    0.12
    Activations Density 0.324%

    No Known Activations