© 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. 87604
    Prev
    Next
    INDEX
    Explanations

    promise or vow

    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
    Pas
    -0.11
    _pas
    -0.11
    olic
    -0.11
    amo
    -0.11
    <quote
    -0.10
     alike
    -0.10
    ode
    -0.10
    cheid
    -0.10
     PAS
    -0.10
     welcome
    -0.10
    POSITIVE LOGITS
     promises
    0.14
     promise
    0.13
     swore
    0.12
     promised
    0.11
     swear
    0.10
     oath
    0.10
     vow
    0.10
     faithfully
    0.10
    promise
    0.09
     solemn
    0.09
    Activations Density 0.006%

    No Known Activations