© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9021
    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
     progressDialog
    -0.27
    æĸĩæľ¬
    -0.26
    _far
    -0.25
     swapped
    -0.24
    à¸ķà¸Ļ
    -0.24
    beer
    -0.23
    åĪ¶åº¦æĶ¹éĿ©
    -0.23
     answered
    -0.23
    èij©
    -0.23
    èĢĥ
    -0.23
    POSITIVE LOGITS
    aid
    0.31
    ÄĽ
    0.24
     coll
    0.24
     Crab
    0.24
     Coll
    0.23
    åį§
    0.23
    ouve
    0.23
     assist
    0.23
    çīµå¼ķ
    0.23
     Publications
    0.23
    Activations Density 0.490%

    No Known Activations

    This feature has no known activations.