© 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. 46112
    Prev
    Next
    INDEX
    Explanations

    flexible or elastic

    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
    nak
    -0.10
    icast
    -0.09
     Teil
    -0.09
    -spe
    -0.09
    iker
    -0.09
     Tul
    -0.09
    ikal
    -0.09
    mak
    -0.08
    cheng
    -0.08
     Listings
    -0.08
    POSITIVE LOGITS
    /stretch
    0.21
    -flex
    0.16
    flex
    0.13
     bend
    0.12
     flexible
    0.12
     bending
    0.12
     Flexible
    0.12
     bends
    0.12
     elasticity
    0.12
     flexibility
    0.12
    Activations Density 0.099%

    No Known Activations