© 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. 128960
    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
    å©·
    -0.27
    ).__
    -0.25
    å®ģåİ¿
    -0.23
    ä¸ĢåĪ»
    -0.23
    ption
    -0.23
    åī¯éĻ¢éķ¿
    -0.23
    æ¿ĥ
    -0.23
    _sur
    -0.23
    åĪ»
    -0.23
     escal
    -0.22
    POSITIVE LOGITS
    æŀª
    0.29
    å±Ģ
    0.27
    åħ¨æĸĩ
    0.27
    çݯçIJĥ
    0.26
    onomies
    0.25
    æľīæīĢ
    0.25
    骨
    0.25
    .gpu
    0.24
    immer
    0.24
    åĽĽå¤Ħ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.