© 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. 90519
    Prev
    Next
    INDEX
    Explanations

    explains / explanation

    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
     immediately
    -0.11
     agreeing
    -0.10
     instinct
    -0.10
     agreed
    -0.10
     vow
    -0.10
     immediate
    -0.09
     instantly
    -0.09
     accepts
    -0.09
     agree
    -0.09
     accept
    -0.09
    POSITIVE LOGITS
     explain
    0.27
     explained
    0.27
     explains
    0.26
     explanation
    0.26
     explaining
    0.25
     explanations
    0.23
     Explanation
    0.22
    explain
    0.22
     Explain
    0.21
    explained
    0.19
    Activations Density 0.082%

    No Known Activations