© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98602
    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
     span
    -0.27
    emento
    -0.27
    \:
    -0.24
    cheon
    -0.24
    æ´ĭ
    -0.24
    ICON
    -0.24
     Balt
    -0.23
    nÄħ
    -0.23
     driv
    -0.23
    ungi
    -0.23
    POSITIVE LOGITS
    çĶŁæ´»è´¨éĩı
    0.26
    åĨįä¹Łæ²¡æľī
    0.25
     removeFrom
    0.25
     removeAll
    0.24
    åĴĮä»ĸçļĦ
    0.24
    èģ¯åIJĪ
    0.24
    并ä¸į代表
    0.24
    åıijçĶŁçļĦ
    0.23
    пп
    0.23
    è³ĩæºIJ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.