© 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. 5397
    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
    iated
    -0.30
     *)__
    -0.26
     Orleans
    -0.25
    anych
    -0.25
    antz
    -0.24
    .lazy
    -0.24
     ims
    -0.24
     hydrated
    -0.24
    è¯Ń
    -0.24
    èѦ
    -0.24
    POSITIVE LOGITS
     outright
    0.32
    åĥ»
    0.30
    ä¸įå¼Ģ
    0.29
     repl
    0.28
    æİ¥
    0.27
    eam
    0.27
    éĻĮçĶŁ
    0.27
    å°ıéķĩ
    0.25
     repost
    0.25
    æī¼
    0.24
    Activations Density 0.241%

    No Known Activations

    This feature has no known activations.