© 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. 98976
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦ表çİ°
    -0.28
    夥
    -0.26
    æİ¥è¿ĩ
    -0.25
    ertime
    -0.24
    /devices
    -0.24
     kitchens
    -0.24
     ages
    -0.23
    å±ħ室
    -0.23
    åݨæĪ¿
    -0.23
    erten
    -0.22
    POSITIVE LOGITS
    æ¡Ī
    0.28
     âĢ¦
    0.26
     ban
    0.25
     exiting
    0.25
    âĢ¦↵↵
    0.25
    åħ¶å®ĥéĹ®é¢ĺ
    0.24
     "
    0.24
    I
    0.24
    ä¼ı
    0.24
     even
    0.23
    Activations Density 0.005%

    No Known Activations