© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25756
    Prev
    Next
    INDEX
    Explanations

    regularly participate or perform

    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
     remind
    -0.11
    wan
    -0.10
     congrat
    -0.09
     teasing
    -0.09
     confirm
    -0.09
    know
    -0.09
    warn
    -0.08
    ÙĬر
    -0.08
     ensure
    -0.08
    uvre
    -0.08
    POSITIVE LOGITS
     participate
    0.18
     participates
    0.16
     perform
    0.16
     participated
    0.16
     Particip
    0.14
     undergo
    0.14
     conduct
    0.14
    è¿Ľè¡Į
    0.14
     engage
    0.13
     engaged
    0.13
    Activations Density 1.052%

    No Known Activations