© 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. 25214
    Prev
    Next
    INDEX
    Explanations

    stepping out of comfort zone

    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
    776
    -0.10
     Tib
    -0.10
     blame
    -0.10
     obsess
    -0.09
     Lug
    -0.09
     Fix
    -0.09
     relieved
    -0.09
     sneak
    -0.09
     blessing
    -0.09
    spiel
    -0.09
    POSITIVE LOGITS
     uncomfortable
    0.40
     discomfort
    0.36
     uncomfort
    0.30
     unfamiliar
    0.28
     challenging
    0.26
     challenge
    0.24
     challenged
    0.23
     stretch
    0.22
    challenge
    0.21
     Challenge
    0.20
    Activations Density 0.117%

    No Known Activations