© 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. 30-TRANSCODER-HP
    7. 94923
    Prev
    Next
    INDEX
    Explanations

    foreign language tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Crimes
    -0.26
    usan
    -0.26
     Krish
    -0.25
    double
    -0.25
    ungi
    -0.25
    _devices
    -0.24
     Pru
    -0.24
    try
    -0.24
     mirror
    -0.24
     match
    -0.24
    POSITIVE LOGITS
    éķ¿è¿ľ
    0.28
    详
    0.27
    xab
    0.26
    ä¸Ģä½ĵ
    0.26
    Ryan
    0.26
    彪
    0.25
    assoc
    0.24
    éĻįä½İäºĨ
    0.24
    uar
    0.24
    _revision
    0.24
    Activations Density 0.001%

    No Known Activations