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. 54181
    Prev
    Next
    INDEX
    Explanations

    iTunes

    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
     tables
    -0.29
    quet
    -0.29
    éħ¬
    -0.26
    &action
    -0.26
    -print
    -0.25
    --↵
    -0.24
    ç²¾åĬĽ
    -0.24
    Tables
    -0.24
     Soc
    -0.24
    ISC
    -0.24
    POSITIVE LOGITS
    çŁ¾
    0.28
    uido
    0.27
    ffer
    0.26
    midt
    0.26
    chied
    0.26
     Serif
    0.25
    è¦ģéĹ»
    0.25
     órg
    0.25
    ourcem
    0.24
     Notices
    0.24
    Activations Density 0.150%

    No Known Activations