© 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. 92645
    Prev
    Next
    INDEX
    Explanations

    winding and wound up

    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
    bara
    -0.10
     Luck
    -0.09
    enze
    -0.09
    ENA
    -0.09
    inus
    -0.09
    íĮ
    -0.09
    ifu
    -0.08
    allon
    -0.08
    iterated
    -0.08
     Watkins
    -0.08
    POSITIVE LOGITS
     tighter
    0.15
     clock
    0.13
     wound
    0.13
     winding
    0.12
     up
    0.12
     clocks
    0.12
     tightly
    0.12
     tightening
    0.11
     Clock
    0.11
     tighten
    0.11
    Activations Density 0.021%

    No Known Activations