© 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. 111044
    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
    spin
    -0.30
     nutshell
    -0.27
    åIJĪ
    -0.27
    rends
    -0.26
     robert
    -0.25
    å®ŀè·µä¸Ń
    -0.25
    è§Ħç¨ĭ
    -0.25
     spin
    -0.24
    ä¸įåIJĪ
    -0.24
    AppState
    -0.24
    POSITIVE LOGITS
     Advertisement
    0.25
    è¿
    0.25
    “
    0.24
    hesion
    0.24
     intersection
    0.24
    he
    0.24
    æĭĸ
    0.24
    ushman
    0.24
    adem
    0.23
     repost
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.