© 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. 5785
    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
    iere
    -0.27
     lear
    -0.26
    ano
    -0.26
    ä¸įçĦ¶
    -0.26
     Trot
    -0.25
    arb
    -0.25
    iators
    -0.25
     Metro
    -0.25
     motives
    -0.25
    å¦Ĥæŀľæ²¡æľī
    -0.25
    POSITIVE LOGITS
    burgh
    0.29
    лÑİÑĩ
    0.27
    åĬĽæ±Ĥ
    0.27
    shoot
    0.26
    beans
    0.25
    èµ°åĬ¿åĽ¾
    0.25
    å»¶è¿Ł
    0.25
    :utf
    0.24
    ä¸įæĸŃåľ°
    0.24
    æijĦåĥı
    0.24
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.