© 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. 86807
    Prev
    Next
    INDEX
    Explanations

    way

    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
    docs
    -0.27
    otti
    -0.27
    ä¸ľæµ·
    -0.26
    ustry
    -0.26
    _keys
    -0.25
    åħ¨çIJĥç»ıæµİ
    -0.25
    oxy
    -0.24
    éĶŁ
    -0.24
    iston
    -0.24
    aten
    -0.24
    POSITIVE LOGITS
     BAT
    0.24
    ught
    0.24
     ano
    0.24
     Spacer
    0.24
     hoe
    0.24
     overwhel
    0.23
    没æľīå¿ħè¦ģ
    0.23
    æİĤ
    0.23
    -appointed
    0.22
    BAT
    0.22
    Activations Density 0.001%

    No Known Activations