© 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. 111563
    Prev
    Next
    INDEX
    Explanations

    silence or stare

    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
    edis
    -0.10
    @email
    -0.10
     Wanted
    -0.10
     Nikol
    -0.10
    &type
    -0.10
     imperson
    -0.09
    mentions
    -0.09
    Ping
    -0.09
    ynam
    -0.08
    llib
    -0.08
    POSITIVE LOGITS
     silence
    0.15
     silent
    0.15
     exchange
    0.15
     exchanged
    0.14
     stare
    0.13
     stares
    0.12
     silently
    0.12
    silent
    0.11
     stared
    0.11
     relocate
    0.11
    Activations Density 0.021%

    No Known Activations