© 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. 5933
    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
    çĶŁäº§æĢ»
    -0.29
    (TM
    -0.25
    otton
    -0.25
    oa
    -0.25
    urgeon
    -0.24
     havoc
    -0.24
    泪
    -0.24
    ogy
    -0.24
    VML
    -0.23
    esthetic
    -0.23
    POSITIVE LOGITS
     foss
    0.30
    ä¸Ģéģį
    0.26
    uman
    0.26
    åĽ´
    0.26
    ForResource
    0.25
    éĽĨåIJĪ
    0.25
    quer
    0.25
    å±ī
    0.24
    ç¼Ģ
    0.24
     Scotia
    0.24
    Activations Density 0.265%

    No Known Activations

    This feature has no known activations.