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. 97813
    Prev
    Next
    INDEX
    Explanations

    specify

    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
    lesc
    -0.27
    unci
    -0.26
    _tex
    -0.25
    æĴij
    -0.25
    encies
    -0.24
    å®ĺ宣
    -0.24
    etherlands
    -0.24
    ancies
    -0.24
     Flux
    -0.24
     PPC
    -0.24
    POSITIVE LOGITS
     pragma
    0.31
     poison
    0.26
     newPath
    0.26
    èѦ
    0.24
    spb
    0.24
    ROUND
    0.23
    çļĦçľ¼åħī
    0.23
    Precision
    0.23
    ,new
    0.23
    auled
    0.23
    Activations Density 0.003%

    No Known Activations