© 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. 5992
    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
    åī§ç»Ħ
    -0.27
    ä¸įè´Ł
    -0.25
    kor
    -0.24
    DOWN
    -0.24
    Org
    -0.24
    æľīæĿ¡ä»¶çļĦ
    -0.24
    Signals
    -0.24
    æľ¬æĽ¸
    -0.23
     Signals
    -0.23
     impatient
    -0.23
    POSITIVE LOGITS
    Âł
    0.26
    è¿ĺä¼ļ
    0.26
    clusions
    0.25
    æŀī
    0.25
    åħ±äº«
    0.25
     region
    0.24
    éĢļ
    0.24
     ring
    0.23
    ·
    0.23
     container
    0.23
    Activations Density 0.916%

    No Known Activations

    This feature has no known activations.