© 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. 111129
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    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
    éĢ»è¾ij
    -0.26
     HelloWorld
    -0.26
    fbe
    -0.25
    ç¿°
    -0.25
     explodes
    -0.25
     Carlton
    -0.25
    onomy
    -0.24
    ç¼Ľ
    -0.24
     workshops
    -0.24
    Early
    -0.24
    POSITIVE LOGITS
    èijµ
    0.28
    ç¾İçĻ½
    0.28
    主è¦ģçĶ¨äºİ
    0.28
     tablets
    0.27
    HING
    0.26
    åįĥæĸ¹çĻ¾
    0.25
    åı£å²¸
    0.25
    ä¸Ģ线
    0.25
     nothing
    0.25
     az
    0.24
    Activations Density 0.013%

    No Known Activations