© 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. 98946
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ernal
    -0.27
    tha
    -0.26
     handleMessage
    -0.26
    ahl
    -0.26
     thr
    -0.24
    åĨħåľ°
    -0.24
    Ljava
    -0.24
    大éĻĨ
    -0.24
    åŁİéĩĮ
    -0.24
     contact
    -0.23
    POSITIVE LOGITS
    asmus
    0.28
    endoza
    0.27
    rack
    0.26
    íĤ¨
    0.26
     Strict
    0.26
    ä¸Ģç«Ļ
    0.25
    Strict
    0.25
    rabbit
    0.24
    ä¸¥æł¼
    0.24
     seeker
    0.23
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.