© 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. 5724
    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
    (after
    -0.26
    羯
    -0.26
    צ×ij
    -0.25
    oop
    -0.25
    票
    -0.24
    æ¯Ľæ³½
    -0.24
    -Am
    -0.24
     convertible
    -0.24
     Albania
    -0.23
    èIJ½åı¶
    -0.23
    POSITIVE LOGITS
    irá
    0.26
    so
    0.26
    管å±Ģ
    0.25
    éĢ®
    0.24
    ¿
    0.24
    lá
    0.23
    lain
    0.23
    EMPL
    0.23
    _refl
    0.23
    ØŃا
    0.23
    Activations Density 0.143%

    No Known Activations

    This feature has no known activations.