© 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. 131246
    Prev
    Next
    INDEX
    Explanations

    scientific/technical documents

    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
    èĮĥåĽ´åĨħ
    -0.29
    führung
    -0.27
     hardware
    -0.26
    _Main
    -0.24
    åĬª
    -0.24
     Mich
    -0.24
     Hardware
    -0.24
    \F
    -0.24
    人æ°ijæĶ¿åºľ
    -0.23
    硬件
    -0.23
    POSITIVE LOGITS
     Boards
    0.26
    è·³èĪŀ
    0.26
    pel
    0.25
     rej
    0.24
    ä¸įå¾Ĺ转载
    0.24
    æĮĩ
    0.24
    èī¯
    0.23
     boards
    0.23
    çµ®
    0.23
     waived
    0.23
    Activations Density 0.009%

    No Known Activations