© 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. 87777
    Prev
    Next
    INDEX
    Explanations

    notoriously unreliable, habit of, known as

    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
     Sadd
    -0.09
    rex
    -0.08
    rou
    -0.08
    roz
    -0.08
     Mold
    -0.08
    TW
    -0.08
    MX
    -0.08
     stale
    -0.07
    halt
    -0.07
    HD
    -0.07
    POSITIVE LOGITS
     tendency
    0.60
     tendencies
    0.49
     notorious
    0.47
     notoriously
    0.43
     propensity
    0.41
     habit
    0.41
     prone
    0.41
     tends
    0.41
     tend
    0.40
     tended
    0.36
    Activations Density 0.362%

    No Known Activations