© 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. 8791
    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
    åıijæĮ¥ä½ľçĶ¨
    -0.26
    éĶĪ
    -0.25
    åıijæĮ¥äºĨ
    -0.25
    -ins
    -0.25
    “
    -0.25
    acity
    -0.24
    ä¼ļåıijçĶŁ
    -0.24
    ì»´
    -0.24
     comp
    -0.24
    åIJĮä¸Ģ个
    -0.24
    POSITIVE LOGITS
    coop
    0.30
    onica
    0.28
    çļĦé«ĺ度
    0.27
    **)&
    0.26
    Ä°Åŀ
    0.26
    ENTA
    0.25
     GANG
    0.25
    аÑĢÑĮ
    0.25
    åįĥæĸ¹
    0.25
    çĸĸ
    0.24
    Activations Density 0.030%

    No Known Activations

    This feature has no known activations.