© 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. 23-TRANSCODER-HP
    7. 162404
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĮĩçĿĢ
    -0.28
    å»·
    -0.26
     adoles
    -0.26
    dpi
    -0.25
    æĺ¯æĮĩ
    -0.25
    称ä¹ĭ为
    -0.24
    ä¸įæĦ¿
    -0.24
    inas
    -0.24
    ceptor
    -0.24
    åħ±æľī
    -0.24
    POSITIVE LOGITS
    _party
    0.26
     DevComponents
    0.26
    iete
    0.25
    æĸ°çļĦä¸Ģ
    0.25
    祸
    0.25
    åħ¨æ°ij
    0.24
    brain
    0.24
    öst
    0.24
    arity
    0.24
    ITTER
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.