© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111440
    Prev
    Next
    INDEX
    Explanations

    repeat or alternatively

    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
    Negative Logits
     Firstly
    -0.11
     stripped
    -0.10
     Lets
    -0.10
     strip
    -0.10
     Lew
    -0.10
     planned
    -0.09
     therefore
    -0.09
     nevertheless
    -0.09
     insult
    -0.09
     Therefore
    -0.09
    POSITIVE LOGITS
     alternatively
    0.20
     altern
    0.18
     Repeat
    0.17
     Alternatively
    0.16
     Optionally
    0.16
     optionally
    0.15
    Repeat
    0.15
     alternate
    0.15
    Alternatively
    0.15
     repeat
    0.14
    Activations Density 0.073%

    No Known Activations