© 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. 27425
    Prev
    Next
    INDEX
    Explanations

    discuss, improve, generate, import

    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
     intentionally
    -0.13
     deliberately
    -0.13
     secretly
    -0.12
     boldly
    -0.12
     fiercely
    -0.11
     abruptly
    -0.10
     purposely
    -0.10
     meticulously
    -0.10
     Eck
    -0.10
     provoc
    -0.10
    POSITIVE LOGITS
     lesson
    0.12
     Lesson
    0.12
     useful
    0.11
     christ
    0.11
     appet
    0.11
     permanent
    0.11
     Permanent
    0.11
     proper
    0.10
     further
    0.10
    lesson
    0.10
    Activations Density 0.016%

    No Known Activations