© 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. 112855
    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
    容
    -0.28
    ç¿ģ
    -0.28
    å¦Ĥä½ķ
    -0.28
    åħ¨çIJĥ
    -0.27
    å¾ģ
    -0.26
    åĪ°
    -0.25
    æķ´
    -0.25
    theses
    -0.25
    åѦ
    -0.25
    说
    -0.24
    POSITIVE LOGITS
    PAD
    0.25
    _COMPARE
    0.25
    æ¨Ĺ
    0.25
     thy
    0.23
    oted
    0.23
    .square
    0.23
    ĻĤ
    0.23
    äºĨä»ĸçļĦ
    0.22
    _SF
    0.22
     mus
    0.22
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.