© 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. 5943
    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
     wink
    -0.28
    å°ģ
    -0.28
    æĬ¹
    -0.27
    доÑĢ
    -0.26
     overshadow
    -0.25
    è°ĥåĬ¨
    -0.25
    æĭĤ
    -0.24
    çijķ
    -0.23
    Javascript
    -0.23
     packaging
    -0.23
    POSITIVE LOGITS
    ONO
    0.30
    fter
    0.27
    slideDown
    0.27
    ç¶ļãģį
    0.27
    çIJĨ
    0.27
    би
    0.26
     getNext
    0.26
    rzy
    0.25
    åĪ«
    0.25
    çľĭæ³ķ
    0.25
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.