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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7372
    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
     le
    -0.29
    æĢ¥
    -0.28
     L
    -0.26
     oss
    -0.26
    __
    -0.26
     el
    -0.26
     T
    -0.25
    å§Ķ
    -0.25
     luc
    -0.25
     pe
    -0.25
    POSITIVE LOGITS
     заб
    0.30
    çľ¼éĩĮ
    0.28
     dope
    0.28
    ModelProperty
    0.27
    oppable
    0.26
    IntArray
    0.26
    è¢Ĥ
    0.26
    家åĸ»
    0.25
    çıĢ
    0.25
    ovies
    0.25
    Activations Density 0.071%

    No Known Activations

    This feature has no known activations.