© 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. 18411
    Prev
    Next
    INDEX
    Explanations

    action or assistance

    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
     fo
    -0.10
     Hyper
    -0.09
     Fo
    -0.09
    ikon
    -0.09
    ihan
    -0.09
     Abr
    -0.08
     limits
    -0.08
     Limits
    -0.08
     progressively
    -0.08
    irk
    -0.08
    POSITIVE LOGITS
     nud
    0.33
     boost
    0.26
     push
    0.24
     encouragement
    0.24
     kick
    0.23
     assistance
    0.21
     Boost
    0.19
     Kick
    0.19
    boost
    0.19
     needed
    0.19
    Activations Density 0.200%

    No Known Activations