© 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. 46264
    Prev
    Next
    INDEX
    Explanations

    evaporate or vaporize

    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
    Not in Any Lists

    No Comments

    Negative Logits
    outh
    -0.09
     Modal
    -0.09
     cram
    -0.09
     barred
    -0.09
     modal
    -0.09
    leur
    -0.08
    modal
    -0.08
    inki
    -0.08
     quel
    -0.08
     topp
    -0.08
    POSITIVE LOGITS
     evapor
    0.28
     vapor
    0.25
     vap
    0.21
     Vapor
    0.21
     ev
    0.20
     Ev
    0.20
    -cond
    0.19
     cond
    0.18
    cond
    0.16
     volatile
    0.16
    Activations Density 0.059%

    No Known Activations