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. 15122
    Prev
    Next
    INDEX
    Explanations

    to

    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
     reflected
    -0.33
     reflecting
    -0.30
    Reflect
    -0.28
     reflective
    -0.28
     reflections
    -0.28
     reflects
    -0.28
    reflect
    -0.28
    ós
    -0.27
     reflection
    -0.27
     Reflect
    -0.26
    POSITIVE LOGITS
     discover
    0.40
     discovery
    0.35
     find
    0.34
     go
    0.33
     read
    0.30
    åıijçݰ
    0.30
     goto
    0.30
     Discovery
    0.29
     audition
    0.28
    ä¸įåģľçļĦ
    0.28
    Activations Density 0.071%

    No Known Activations