© 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. 5938
    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
    ,port
    -0.28
    ạng
    -0.26
    åIJĬ顶
    -0.26
    :.
    -0.25
     port
    -0.25
    onne
    -0.25
     Quickly
    -0.25
    \Factory
    -0.24
     Port
    -0.24
    alten
    -0.24
    POSITIVE LOGITS
    pard
    0.27
     eslint
    0.25
    æī¯
    0.24
     unthinkable
    0.24
    IFEST
    0.24
    -Jun
    0.24
     mpi
    0.23
    æĭīåĬ¨
    0.23
     MP
    0.23
    æŁłæª¬
    0.23
    Activations Density 0.082%

    No Known Activations

    This feature has no known activations.