© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4701
    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
    çļĦä¼łç»Ł
    -0.30
    ä¼łç»Ł
    -0.28
    é¬Ĩ
    -0.26
    åĴĮåıijå±ķ
    -0.25
    rovers
    -0.25
    ArrayOf
    -0.25
    ä¼łç»ŁçļĦ
    -0.25
    æIJ´
    -0.24
     remote
    -0.24
     sensitive
    -0.24
    POSITIVE LOGITS
    믹
    0.26
    mgr
    0.24
    undler
    0.24
    åij¨ä¸Ģ
    0.24
    riers
    0.23
     saddle
    0.23
    adders
    0.23
    apeutics
    0.23
    èĩ§
    0.23
     celestial
    0.23
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.