© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56462
    Prev
    Next
    INDEX
    Explanations

    articles, researchers or authors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èļĵ
    -0.28
    æıł
    -0.26
    EMON
    -0.25
    wis
    -0.24
     domest
    -0.24
    类产åĵģ
    -0.23
     Dix
    -0.23
    IJèĹı
    -0.23
    åIJĪæ³ķæĿĥçĽĬ
    -0.23
     showroom
    -0.22
    POSITIVE LOGITS
    æĬĦ
    0.28
    èĨ
    0.25
    ç©·
    0.25
    é¢Ĩè¡Ķ
    0.25
    åįļ士
    0.25
    _$_
    0.25
     Valerie
    0.24
    å®ļäºĨ
    0.24
    游åĩ»
    0.24
    æīĵåİĭ
    0.24
    Activations Density 0.145%

    No Known Activations