© 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. 20-TRANSCODER-HP
    7. 63698
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     based
    -0.30
     plasma
    -0.27
     çĻ»
    -0.26
    åıĤçħ§
    -0.26
    kop
    -0.25
    å°±æĺ¯ä¸Ģ个
    -0.25
    ges
    -0.25
    Based
    -0.25
    æĺ¯çľŁçļĦ
    -0.24
    based
    -0.24
    POSITIVE LOGITS
    Debugger
    0.29
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.28
    rö
    0.27
    LEY
    0.26
    ******č↵
    0.26
    æīĵçĿĢ
    0.25
    schlä
    0.25
    å¸Ńåį·
    0.24
    éļĶ离
    0.24
    phinx
    0.24
    Activations Density 17.557%

    No Known Activations

    This feature has no known activations.