© 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. 115474
    Prev
    Next
    INDEX
    Explanations

    discussing or talking about

    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
     autobiography
    -0.10
     Butterfly
    -0.09
     capit
    -0.09
     neutrality
    -0.09
     Arn
    -0.09
     Pol
    -0.08
     apology
    -0.08
     solitude
    -0.08
     astr
    -0.08
     sovere
    -0.08
    POSITIVE LOGITS
     discussion
    0.50
     discussing
    0.49
     discussions
    0.46
     discuss
    0.46
     Discuss
    0.43
     Discussion
    0.42
     discussed
    0.41
     discusses
    0.40
    Discuss
    0.39
    Discussion
    0.39
    Activations Density 0.243%

    No Known Activations