© 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. 15786
    Prev
    Next
    INDEX
    Explanations

    want and desire

    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
    elow
    -0.12
     sucess
    -0.12
     Sonia
    -0.12
    ALLOW
    -0.11
     copyrighted
    -0.11
     Ry
    -0.10
     suce
    -0.10
     succesfully
    -0.10
    luck
    -0.10
    -success
    -0.10
    POSITIVE LOGITS
     want
    0.12
     enthusiasm
    0.12
     consensus
    0.12
     genuinely
    0.11
     rethink
    0.11
     consenting
    0.11
     wants
    0.11
     genuine
    0.11
     desire
    0.11
     truly
    0.10
    Activations Density 0.049%

    No Known Activations