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. 11-TRANSCODER-HP
    4. 146289
    Prev
    Next
    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽŀäºĭ
    -0.31
     spans
    -0.27
    çļĦ缮çļĦ
    -0.26
     border
    -0.26
    çļĦç¼ĺ
    -0.25
    ä»£æĽ¿
    -0.25
    ç¼ĺ
    -0.25
    bian
    -0.24
    leness
    -0.24
    ç¼Ģ
    -0.24
    POSITIVE LOGITS
    yclopedia
    0.28
    ä¾ł
    0.28
    éĩĬ
    0.27
     sic
    0.26
    dda
    0.25
    RD
    0.25
    ãĤ¤ãĤ¹
    0.24
    ÅĽci
    0.24
    åįĥä¸ĩ
    0.24
    éĽ·è¾¾
    0.24
    Activations Density 0.004%

    No Known Activations