© 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. 31-TRANSCODER-HP
    7. 18270
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    subject
    -0.29
    寡
    -0.28
    丸
    -0.28
    äºĨä¸Ģ份
    -0.27
    è¿Ļ份
    -0.26
    .subject
    -0.25
    éĺµéĺµ
    -0.25
    屿
    -0.25
    (subject
    -0.24
    æĬķèµĦ人
    -0.24
    POSITIVE LOGITS
     Fu
    0.25
     process
    0.24
    enha
    0.24
     cong
    0.24
     larg
    0.23
    dialogs
    0.23
    ager
    0.23
     cons
    0.23
    udad
    0.23
     Dialog
    0.23
    Activations Density 0.152%

    No Known Activations

    This feature has no known activations.