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. 15236
    Prev
    Next
    INDEX
    Explanations

    politics

    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
    istor
    -0.29
     norms
    -0.28
     comm
    -0.27
    室å¤ĸ
    -0.26
    ç¼Ķ
    -0.26
    (norm
    -0.25
    gary
    -0.25
    ermann
    -0.25
    tone
    -0.25
     craft
    -0.25
    POSITIVE LOGITS
    ìĭŃ
    0.26
     Cluster
    0.26
    ella
    0.26
    åŃĺéĩı
    0.25
    豫
    0.25
    uite
    0.24
    Sphere
    0.24
    Shell
    0.24
    å¿ĥ
    0.23
    Spin
    0.23
    Activations Density 0.102%

    No Known Activations