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. 7-TRANSCODER-HP
    4. 93
    Prev
    Next
    INDEX
    Explanations

    potatoes and Americas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ¥
    -0.26
    oard
    -0.25
    ayah
    -0.25
    å°ĸåı«
    -0.25
    æł¸æ¡ĥ
    -0.25
    åij¨è½¬
    -0.25
     Cheryl
    -0.24
    æĬ¤åį«
    -0.24
    ment
    -0.23
    ologi
    -0.23
    POSITIVE LOGITS
     –↵↵
    0.30
    å°½
    0.29
    æŃ§
    0.28
     -↵↵
    0.27
     +=↵
    0.26
    ä¸Ģåı£
    0.26
    åĽ½æĥħ
    0.26
     mismatch
    0.25
    ä»»
    0.25
    –↵↵
    0.25
    Activations Density 0.003%

    No Known Activations