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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5729
    Prev
    Next
    INDEX
    Explanations

    Code/File 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
     diminish
    -0.29
    zelf
    -0.27
     –
    -0.27
     Pied
    -0.26
     Wings
    -0.26
    éĥ½ä¸įä¼ļ
    -0.25
    Coder
    -0.25
     accounted
    -0.24
     (
    -0.24
     phụ
    -0.24
    POSITIVE LOGITS
    usses
    0.27
    èĬĬ
    0.25
    好åIJ§
    0.25
    edral
    0.25
    antro
    0.24
    ulk
    0.24
    figures
    0.24
    juana
    0.24
    .getBytes
    0.24
    /meta
    0.24
    Activations Density 0.329%

    No Known Activations