© 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. 131025
    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
     jot
    -0.27
    çĨŁç»ĥ
    -0.26
    交éĢļæŀ¢çº½
    -0.25
    rf
    -0.25
    -push
    -0.24
    vell
    -0.24
    ä¼ļåıijçĶŁ
    -0.24
    ague
    -0.23
    auses
    -0.23
    åı¥
    -0.23
    POSITIVE LOGITS
    {s
    0.25
    å®ĺ
    0.25
    å¹´ä¹ĭä¹ħ
    0.25
    adopt
    0.24
    ilde
    0.23
    /self
    0.23
    tempts
    0.23
    åİĨå¹´
    0.23
    åľ¨ç½ijä¸Ĭ
    0.23
    ç»Łè®¡æķ°æį®
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.