© 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. 97213
    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
    enate
    -0.27
    å°½
    -0.26
    tier
    -0.26
    silent
    -0.25
    reau
    -0.25
    对å¾ħ
    -0.24
     radix
    -0.24
    forme
    -0.24
    elan
    -0.24
     Fireplace
    -0.24
    POSITIVE LOGITS
    ecc
    0.29
     Promise
    0.28
    cc
    0.28
    /cc
    0.28
     promise
    0.27
    iswa
    0.26
    åĴ¸
    0.26
    æŃ»åIJİ
    0.26
     Mer
    0.25
     Laz
    0.25
    Activations Density 0.030%

    No Known Activations

    This feature has no known activations.