© 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. 5424
    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
    reff
    -0.29
    otre
    -0.28
    onas
    -0.24
    宽容
    -0.24
    iele
    -0.23
     Attached
    -0.23
    ä¿Ŀè¯ģ
    -0.23
    .Range
    -0.23
     Andersen
    -0.23
    ASSERT
    -0.23
    POSITIVE LOGITS
     mú
    0.28
    æīĵå¾Ĺ
    0.27
    éļ¾
    0.26
    <tag
    0.26
    Exec
    0.25
    ndl
    0.25
    ivil
    0.24
     Worth
    0.24
     multiple
    0.23
    éĤ£æĺ¯
    0.23
    Activations Density 0.065%

    No Known Activations

    This feature has no known activations.