© 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. 20-TRANSCODER-HP
    7. 129174
    Prev
    Next
    INDEX
    Explanations

    Looking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸įéĶĻçļĦ
    -0.27
    epy
    -0.25
    éĩıåĮĸ
    -0.25
    ä¾ĭå¤ĸ
    -0.24
    大åıij
    -0.24
    æľ¬èº«çļĦ
    -0.24
    éĢĤå½ĵ
    -0.24
    æ°¸ä¹ħ
    -0.24
    fore
    -0.23
    çļĦåĬĽéĩı
    -0.23
    POSITIVE LOGITS
    adamente
    0.28
    woke
    0.27
    è§ĦåĪĴ设计
    0.26
     ấy
    0.26
    å°±è¶Ĭ
    0.26
    è¯Ŀ说
    0.26
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    0.25
    unread
    0.25
    æĿĸ
    0.25
     shed
    0.25
    Activations Density 6.546%

    No Known Activations