© 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. 6432
    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
     nipples
    -0.28
    æłĩ
    -0.26
    åŀĵ
    -0.26
    ño
    -0.25
    umeric
    -0.24
    æ¨Ļæºĸ
    -0.24
    cheiden
    -0.24
    earn
    -0.24
    eten
    -0.23
    ear
    -0.23
    POSITIVE LOGITS
     behold
    0.27
     slur
    0.27
     legit
    0.25
    tas
    0.24
    onyms
    0.24
    rama
    0.23
    ä»»
    0.23
    воÑĢ
    0.23
    \brief
    0.23
    ly
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.