© 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. 14147
    Prev
    Next
    INDEX
    Explanations

    feel like, want, taste treat

    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
    STEM
    -0.09
    inea
    -0.09
    ew
    -0.09
     Lew
    -0.09
     Mes
    -0.08
    str
    -0.08
     Skeleton
    -0.08
    underline
    -0.08
     weg
    -0.08
    alfa
    -0.08
    POSITIVE LOGITS
     mood
    0.50
     Mood
    0.41
     craving
    0.28
     tired
    0.24
     cravings
    0.23
     fatigue
    0.22
     hungry
    0.20
     hunger
    0.20
     feeling
    0.20
     crave
    0.20
    Activations Density 0.097%

    No Known Activations