© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16346
    Prev
    Next
    INDEX
    Explanations

    promises and pledges

    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
     welcoming
    -0.11
    wel
    -0.10
    vat
    -0.10
     Dy
    -0.10
    ей
    -0.10
     Wel
    -0.10
     Gdk
    -0.10
    ars
    -0.09
    atten
    -0.09
    alion
    -0.09
    POSITIVE LOGITS
     promise
    0.76
     promises
    0.75
     promised
    0.66
     Promise
    0.58
    promise
    0.54
    Promise
    0.52
     promising
    0.51
     pledge
    0.49
     pledges
    0.49
     vow
    0.48
    Activations Density 0.247%

    No Known Activations