© 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. 5395
    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
     testify
    -0.28
    éĢĢåĽŀ
    -0.27
    und
    -0.25
    æĸ¼
    -0.25
    æ±Ĥ
    -0.25
     fores
    -0.24
    åĮ¿åIJį
    -0.24
     illustr
    -0.24
    æĬ¥è¡¨
    -0.24
    A
    -0.23
    POSITIVE LOGITS
    upe
    0.32
    otron
    0.30
    OLT
    0.26
    _hdl
    0.25
    羣æŃ£åģļåĪ°
    0.25
    说å®ŀ
    0.24
    rtc
    0.24
    mlink
    0.24
    .persist
    0.24
    Ħ件
    0.24
    Activations Density 1.712%

    No Known Activations

    This feature has no known activations.