© 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. 129111
    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
    okit
    -0.28
    setContent
    -0.26
    addock
    -0.25
    etting
    -0.24
    ||(
    -0.24
    ä½ĵåĪ¶
    -0.24
    èĿł
    -0.24
    ä½ĵåĪ¶æĶ¹éĿ©
    -0.24
    ombres
    -0.23
    idding
    -0.23
    POSITIVE LOGITS
    Iss
    0.27
    å¦ĤæѤ
    0.27
    EMA
    0.27
    åľ¨å®¶
    0.26
     so
    0.25
    以æĿ¥
    0.25
     ROS
    0.24
     besides
    0.24
    -Allow
    0.23
    Spr
    0.23
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.