© 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. 5429
    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
    åıijå¸ĥä¼ļ
    -0.29
    .throw
    -0.25
    (ss
    -0.25
    arga
    -0.25
    åIJĪ
    -0.24
     RSS
    -0.24
    åħĪåIJİ
    -0.24
    appa
    -0.24
    ä¼ł
    -0.24
    Superview
    -0.23
    POSITIVE LOGITS
    vard
    0.31
    iard
    0.27
     trib
    0.27
     Amazon
    0.26
    åĪ°è¿ĻéĩĮ
    0.25
    à¸ĵะ
    0.24
    otechn
    0.24
     Lands
    0.24
    ibs
    0.24
    ihan
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.