© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 131170
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    mad
    -0.27
    åķĨä¸ļ模å¼ı
    -0.26
    广
    -0.26
    é¹ħ
    -0.25
    od
    -0.24
    åıªä¸įè¿ĩ
    -0.24
    åįµ
    -0.24
    uc
    -0.24
     complex
    -0.24
    æijĩäºĨæijĩ头
    -0.24
    POSITIVE LOGITS
    iola
    0.28
    ensively
    0.27
     setSupportActionBar
    0.27
     Nä
    0.26
    SCP
    0.26
    -required
    0.25
    _firestore
    0.25
     Unidos
    0.25
    ä¸ĵ人
    0.25
    reten
    0.25
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.