© 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. 5952
    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
     DEAL
    -0.24
    åĩŃ
    -0.24
    <pre
    -0.23
    å°¼äºļ
    -0.23
    ä¹ĭ乡
    -0.23
    èĩªå¦Ĥ
    -0.23
     Critics
    -0.23
    éĽĨåĽ¢èĤ¡ä»½
    -0.23
    iversal
    -0.23
    éĽĨä½ĵç»ıæµİ
    -0.23
    POSITIVE LOGITS
    åį«
    0.26
    kon
    0.26
    conv
    0.26
    -years
    0.25
    èij«èĬ¦
    0.24
    ä½İä¼°
    0.24
    Dan
    0.24
    -level
    0.24
    å¸Ľ
    0.23
     fuzz
    0.23
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.