© 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. 27219
    Prev
    Next
    INDEX
    Explanations

    various different other

    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
     circumstance
    -0.11
     expectation
    -0.08
     implication
    -0.08
     reperc
    -0.08
     limitation
    -0.08
     complication
    -0.08
     insight
    -0.07
     consequence
    -0.07
     type
    -0.07
     capability
    -0.07
    POSITIVE LOGITS
     purposes
    0.15
     statuses
    0.15
     incomes
    0.15
     lifestyles
    0.14
     interpretations
    0.14
     descriptions
    0.14
     meanings
    0.14
     contents
    0.14
     contexts
    0.14
     climates
    0.14
    Activations Density 0.208%

    No Known Activations