© 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. 5866
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    bach
    -0.34
    常
    -0.28
    cast
    -0.28
     cast
    -0.27
    ores
    -0.26
     ngắn
    -0.26
    -angular
    -0.25
    mor
    -0.25
    æľīåĩłä¸ª
    -0.25
    oad
    -0.25
    POSITIVE LOGITS
    -minded
    0.27
    ç²²
    0.27
     Cra
    0.26
     Pey
    0.26
     dj
    0.26
    ãģĥ
    0.26
    bpp
    0.26
    PFN
    0.25
    jian
    0.25
    éĤ£ä»½
    0.25
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.