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. 15103
    Prev
    Next
    INDEX
    Explanations

    What does it mean?

    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
    resents
    -0.34
    rics
    -0.28
    æ¯ķ竣æĺ¯
    -0.28
     knows
    -0.28
     provides
    -0.28
     représ
    -0.28
    defines
    -0.28
    ãģıãĤĮ
    -0.28
    Provide
    -0.28
    æıIJä¾ĽäºĨ
    -0.27
    POSITIVE LOGITS
    被
    0.32
    å®ĥ
    0.31
    (@(
    0.31
     pov
    0.29
    å¹¶
    0.28
    av
    0.27
    ”ãĢĤ
    0.26
     integral
    0.26
     lead
    0.26
    ”)
    0.26
    Activations Density 0.886%

    No Known Activations