© 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. 50809
    Prev
    Next
    INDEX
    Explanations

    web or scopic cryotherapy

    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
     Fancy
    -0.09
     Quiet
    -0.08
    æī
    -0.08
     sisters
    -0.08
     unab
    -0.08
     Shr
    -0.08
     tracing
    -0.07
     uncon
    -0.07
    onto
    -0.07
     "
    -0.07
    POSITIVE LOGITS
    elin
    0.11
    âĢ¦↵↵↵↵
    0.10
    gba
    0.10
     pic
    0.10
    âĢ¦”↵↵
    0.09
    [:]
    0.09
     POST
    0.09
    omat
    0.09
    eday
    0.09
     âĹı
    0.09
    Activations Density 0.011%

    No Known Activations