© 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. 131080
    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
    çݯ
    -0.32
    çĴ°
    -0.27
    iro
    -0.26
    idi
    -0.26
    ooter
    -0.26
    ãĤ«ãĥ³
    -0.26
    uten
    -0.25
    oble
    -0.25
    iros
    -0.25
    寰
    -0.25
    POSITIVE LOGITS
    verty
    0.30
    "](
    0.28
     Rays
    0.26
    èĸ°
    0.26
     convers
    0.25
     forthcoming
    0.24
    åħįè´¹
    0.24
    æīĢæıIJä¾Ľ
    0.24
    åį³å°ĨåĪ°æĿ¥
    0.24
    æºĨ
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.