© 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. 47437
    Prev
    Next
    INDEX
    Explanations

    continued continuation repeating repeat

    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
    atz
    -0.10
     momentarily
    -0.10
    anje
    -0.09
    ieber
    -0.09
     finally
    -0.09
    VC
    -0.08
    ären
    -0.08
    andel
    -0.08
     indirectly
    -0.08
     sobie
    -0.08
    POSITIVE LOGITS
     repeat
    0.45
     continued
    0.42
     continuation
    0.40
     repeated
    0.38
     continuing
    0.38
     further
    0.37
     continue
    0.37
     repeats
    0.37
     Repeat
    0.36
     Continued
    0.36
    Activations Density 0.583%

    No Known Activations