© 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. 86915
    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
    è¿ĻäºĽä¸ľè¥¿
    -0.25
    亿
    -0.24
    åİĭæĬij
    -0.24
    æ¥ŀ
    -0.24
     distract
    -0.24
     Rule
    -0.24
    诸侯
    -0.23
    çĶµåŃIJéĤ®ä»¶
    -0.23
    .ak
    -0.23
    åħ¶ä»ĸ人
    -0.23
    POSITIVE LOGITS
    zp
    0.30
    jing
    0.27
    -thumb
    0.27
    ception
    0.26
    ç¥ļ
    0.26
    çļĦçĶŁåij½
    0.26
    ’T
    0.25
     kh
    0.24
     touch
    0.24
    ((__
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.