© 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. 86935
    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
     wild
    -0.29
    Chef
    -0.27
     favor
    -0.25
    chef
    -0.25
     exhib
    -0.24
    wild
    -0.23
    éĩİçĶŁ
    -0.23
    .spark
    -0.23
    æ·±å¤Ħ
    -0.23
    traction
    -0.23
    POSITIVE LOGITS
    æŀ¸
    0.28
    æ¿ĥ
    0.27
     concentrating
    0.26
    åij½
    0.26
     concentrate
    0.25
     quoi
    0.25
     glimpse
    0.25
     concentration
    0.24
     acquire
    0.24
     surpr
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.