© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2739
    Prev
    Next
    INDEX
    Explanations

    feel followed by an adjective or "a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     visibly
    -0.10
     thinking
    -0.08
     skyline
    -0.08
    ÑĮ
    -0.08
    eral
    -0.08
    cks
    -0.08
    sal
    -0.08
    ative
    -0.07
     pleasing
    -0.07
     shar
    -0.07
    POSITIVE LOGITS
     obligated
    0.12
     sorry
    0.11
     confident
    0.11
    ibur
    0.11
     cheated
    0.10
     lucky
    0.10
     safe
    0.10
    GBT
    0.10
     compelled
    0.10
     fortunate
    0.10
    Activations Density 0.039%

    No Known Activations