© 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. 130723
    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
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.28
    ressing
    -0.26
    é«ĺå°ļ
    -0.25
    âĢ¦↵↵
    -0.24
    çĦ¦çĤ¹
    -0.24
    çīĩ
    -0.24
    èľķ
    -0.24
    âĢ¦
    -0.23
    äºĨä¸Ģ个
    -0.23
    æŃ¥æŃ¥
    -0.23
    POSITIVE LOGITS
    undi
    0.25
    溯æºIJ
    0.25
    ology
    0.24
    omit
    0.24
    odia
    0.24
    .repo
    0.23
    .bz
    0.23
     xếp
    0.23
    à¸Ħà¸Ń
    0.23
    ipi
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.