© 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. 113109
    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
    æŀķ
    -0.27
    ulo
    -0.25
    解读
    -0.25
    ÑĦÑĢ
    -0.24
    ption
    -0.24
    arning
    -0.24
    ivals
    -0.24
    èĪĴ
    -0.23
    ushing
    -0.23
    dam
    -0.23
    POSITIVE LOGITS
     opendir
    0.28
     Dynam
    0.25
    mploy
    0.24
    å¼¹
    0.24
     ={↵
    0.23
    ëĬĺ
    0.23
    _DECLARE
    0.23
     Kam
    0.23
    å®ĭ代
    0.23
    .bindingNavigator
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.