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. 23-TRANSCODER-HP
    4. 162278
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · 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
    strup
    -0.26
    æİ¨èįIJ
    -0.26
    ียà¸ĩ
    -0.26
    ç³»
    -0.26
     dream
    -0.26
     recommended
    -0.25
     esp
    -0.25
    ç¯Ļ
    -0.25
    MP
    -0.24
    梦è§ģ
    -0.24
    POSITIVE LOGITS
    abble
    0.30
    иÑĪ
    0.27
    shuffle
    0.27
     Cheney
    0.27
     halt
    0.25
     Sphere
    0.24
     Subset
    0.24
    adox
    0.23
     Saying
    0.23
     Cylinder
    0.23
    Activations Density 0.004%

    No Known Activations