© 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. 15956
    Prev
    Next
    INDEX
    Explanations

    expressions of feelings or statements

    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
     Suggestions
    -0.11
     interes
    -0.11
    eor
    -0.11
     Strike
    -0.10
     description
    -0.10
     suggestive
    -0.10
    friendly
    -0.10
    Strike
    -0.10
    Description
    -0.10
     Description
    -0.10
    POSITIVE LOGITS
     declaration
    0.15
     declarations
    0.15
     profess
    0.15
     expressed
    0.15
     express
    0.15
     verbal
    0.14
     affirmation
    0.14
     sincerity
    0.14
     verbally
    0.14
    express
    0.13
    Activations Density 0.031%

    No Known Activations