© 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. 88901
    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
     foil
    -0.24
     %@
    -0.23
    éĩįéĩı
    -0.22
    ãĤ·ãĥª
    -0.22
    á»Ķ
    -0.22
    åħĪè¡Į
    -0.22
     precedence
    -0.22
    Ķ
    -0.22
     OSP
    -0.21
    >"č↵
    -0.21
    POSITIVE LOGITS
    çªķ
    0.27
    大声
    0.26
    ä¸Ģå¤Ħ
    0.25
    åĪĽéĢł
    0.24
    éĢļè¯Ŀ
    0.24
    ä¸įçŁ¥
    0.23
    对åħ¶è¿Ľè¡Į
    0.23
    å°½åĬĽ
    0.23
    åı®åĺ±
    0.23
    Episode
    0.22
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.