© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8401
    Prev
    Next
    INDEX
    Explanations

    Code/technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orts
    -0.26
    <center
    -0.26
    <table
    -0.26
    icap
    -0.25
    ç½Ķ
    -0.25
    ucci
    -0.25
    çĥŁåĽ±
    -0.24
    <select
    -0.24
     ones
    -0.24
    æ·¯
    -0.24
    POSITIVE LOGITS
    axy
    0.27
    год
    0.26
    XP
    0.26
    宪
    0.25
    hm
    0.25
    å¸ĪèĮĥ大åѦ
    0.24
    undred
    0.24
    æ°ı
    0.24
    Thêm
    0.24
    åijĥ
    0.24
    Activations Density 0.154%

    No Known Activations