© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115412
    Prev
    Next
    INDEX
    Explanations

    benefit from quantity

    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
     pref
    -0.11
     Mood
    -0.11
    BUY
    -0.10
     cough
    -0.10
     Brewer
    -0.10
    acco
    -0.10
     Scre
    -0.10
    look
    -0.10
     loaded
    -0.09
     Awake
    -0.09
    POSITIVE LOGITS
     pleasure
    0.33
     enjoyment
    0.32
     benefit
    0.30
     satisfaction
    0.25
     Benefit
    0.22
     benefits
    0.21
     joy
    0.21
     pleasures
    0.19
     benefited
    0.19
     amusement
    0.18
    Activations Density 0.129%

    No Known Activations