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. 15084
    Prev
    Next
    INDEX
    Explanations

    manual

    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
    agas
    -0.26
     Parkway
    -0.24
     Sydney
    -0.24
    obra
    -0.24
    .hits
    -0.24
    gx
    -0.24
    åħ¶
    -0.24
    æľīä½ķ
    -0.24
    å¼¹
    -0.24
    ç³»
    -0.23
    POSITIVE LOGITS
    dia
    0.31
     dressing
    0.29
    tons
    0.28
    isko
    0.28
    ize
    0.28
    æīĵæī®
    0.28
    ised
    0.28
    istic
    0.27
    methods
    0.27
     methods
    0.27
    Activations Density 0.045%

    No Known Activations