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. 1704
    Prev
    Next
    INDEX
    Explanations

    virtual servers

    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
    urat
    -0.28
    åı¹
    -0.25
    turtle
    -0.24
    avenport
    -0.24
     BBB
    -0.24
    æļĿ
    -0.23
    æŃ£çīĪ
    -0.23
    PARSE
    -0.23
     Gol
    -0.23
    ;"></
    -0.23
    POSITIVE LOGITS
    nı
    0.28
    横
    0.26
     norm
    0.25
    åįģåŃĹ
    0.25
    åķĨä¸ļåĮĸ
    0.24
    nings
    0.24
    ãĥ¼ãĤ¿ãĥ¼
    0.24
     Steam
    0.24
    ä¸Ńå¤ĸ
    0.24
    èĴ¸æ±½
    0.24
    Activations Density 0.001%

    No Known Activations