© 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. 16648
    Prev
    Next
    INDEX
    Explanations

    asked to participate or serve

    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
    vic
    -0.10
     vic
    -0.10
    jr
    -0.09
    writers
    -0.09
     ric
    -0.08
     metro
    -0.08
    äº
    -0.08
     freely
    -0.08
     Douglas
    -0.08
     desire
    -0.08
    POSITIVE LOGITS
     participate
    0.15
     participates
    0.14
     testify
    0.13
    åıĤ
    0.12
     participated
    0.12
     participating
    0.12
     unexpectedly
    0.12
     Particip
    0.12
     urgently
    0.11
     participation
    0.10
    Activations Density 0.143%

    No Known Activations