© 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. 7714
    Prev
    Next
    INDEX
    Explanations

    continue / continuing

    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
    aset
    -0.11
    ARN
    -0.08
    Await
    -0.08
     unpack
    -0.08
     intervened
    -0.08
     intervene
    -0.08
     interven
    -0.08
    OPEN
    -0.08
    jc
    -0.08
    fp
    -0.07
    POSITIVE LOGITS
     continued
    0.64
     continue
    0.64
     continuing
    0.62
     continues
    0.59
     Continue
    0.56
     continuation
    0.54
    continue
    0.52
     Continuing
    0.51
     Continued
    0.50
    Continue
    0.49
    Activations Density 0.189%

    No Known Activations