© 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. 6007
    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
    activity
    -0.28
    æ´»åĬ¨ä¸Ń
    -0.28
     Copp
    -0.25
     cá»Ń
    -0.25
    arium
    -0.24
    åĪĨåħ¬åı¸
    -0.24
    æ´»åĭķ
    -0.24
    dorf
    -0.24
    ünd
    -0.24
     free
    -0.24
    POSITIVE LOGITS
     opport
    0.28
    åĪĩ
    0.27
     ide
    0.26
    IBUT
    0.25
    ÙĤباÙĦ
    0.24
    ayo
    0.24
    é¢ľåĢ¼
    0.24
    icz
    0.24
    tero
    0.23
    åķĥ
    0.23
    Activations Density 0.228%

    No Known Activations

    This feature has no known activations.