© 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. 16076
    Prev
    Next
    INDEX
    Explanations

    fulfilled, satisfying, met, or disappointed

    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
     overrun
    -0.10
    hek
    -0.08
    erness
    -0.08
     punct
    -0.08
     Cousins
    -0.08
    Agents
    -0.08
    pta
    -0.08
    mers
    -0.08
     gul
    -0.08
     Wel
    -0.08
    POSITIVE LOGITS
    elay
    0.10
    Scaler
    0.10
    glob
    0.09
    رÙĪ
    0.09
    ment
    0.09
     Pam
    0.09
     whichever
    0.09
    eee
    0.09
    ee
    0.09
     laid
    0.09
    Activations Density 0.007%

    No Known Activations