Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 15188
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names related to individuals and organizations.

    oai_token-act-pair · gpt-4o-miniTriggered by @shantanudarveshi

    the ending "ation" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     noises
    -0.33
     behaviors
    -0.31
     expansions
    -0.31
     orientations
    -0.31
     protections
    -0.30
     meanings
    -0.30
    ITIES
    -0.29
     potentials
    -0.29
    prüf
    -0.28
    tests
    -0.28
    POSITIVE LOGITS
    ization
    0.43
    imation
    0.42
    ification
    0.42
     augmentation
    0.41
    isation
    0.40
    ierung
    0.40
     regulation
    0.40
     automation
    0.40
    ylation
    0.40
    imization
    0.39
    Activations Density 2.024%

    No Known Activations