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. 53885
    Prev
    Next
    INDEX
    Explanations

    causation

    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
    åģĪ
    -0.27
    欺è¯Ī
    -0.26
     indu
    -0.26
    ajar
    -0.24
    鸾
    -0.24
     grosse
    -0.24
     augmented
    -0.24
    ç®Ĺ
    -0.23
    å¿łå®ŀ
    -0.23
    metics
    -0.23
    POSITIVE LOGITS
    个å¤ļ
    0.26
    ä¸ºçĽ®çļĦ
    0.26
    ONGL
    0.25
    ç¬ij
    0.25
    .neo
    0.24
     Crit
    0.24
    BlockSize
    0.24
    顸
    0.24
    \Bridge
    0.23
     debugger
    0.23
    Activations Density 0.027%

    No Known Activations