© 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. 22-TRANSCODER-HP
    7. 130006
    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
    Not in Any Lists

    No Comments

    Negative Logits
    è¡·
    -0.26
    å¤ĸéĥ¨
    -0.25
     veto
    -0.24
    åıijçĶŁ
    -0.24
    平衡
    -0.23
     pros
    -0.23
     exterior
    -0.23
     external
    -0.23
    uty
    -0.23
    rons
    -0.22
    POSITIVE LOGITS
    é£İ湿
    0.26
    饱
    0.25
    etyl
    0.25
    两åı¥
    0.24
    æķ´ä¸ªäºº
    0.24
    åħħ足
    0.23
    CCCC
    0.23
    COPE
    0.23
     gadgets
    0.23
    ãĤĦãĤĬ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.