© 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. 25262
    Prev
    Next
    INDEX
    Explanations

    certainty, assurance, confident

    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
     cult
    -0.09
     Resident
    -0.08
    obia
    -0.08
     moderated
    -0.08
     gloss
    -0.08
     Highlands
    -0.08
    ador
    -0.08
    -license
    -0.08
     high
    -0.07
    rias
    -0.07
    POSITIVE LOGITS
     certainty
    0.41
     cert
    0.27
     Cert
    0.26
     assurance
    0.25
     confident
    0.25
     assured
    0.25
    ç¡®å®ļ
    0.24
    cert
    0.23
     CERT
    0.23
     Assurance
    0.22
    Activations Density 0.016%

    No Known Activations