© 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. 112153
    Prev
    Next
    INDEX
    Explanations

    conversations and discussions

    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
     attracting
    -0.10
    iare
    -0.10
     fou
    -0.09
    ubar
    -0.09
     stepping
    -0.09
    witter
    -0.08
     attracts
    -0.08
     coordin
    -0.08
    ukan
    -0.08
     attracted
    -0.08
    POSITIVE LOGITS
     periodically
    0.21
     discussions
    0.18
     conversations
    0.18
     occasional
    0.17
     occasionally
    0.17
     verbally
    0.17
     Occasionally
    0.16
     Discussions
    0.16
     Convers
    0.15
     openly
    0.15
    Activations Density 0.027%

    No Known Activations