© 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. 27-TRANSCODER-HP
    7. 58358
    Prev
    Next
    INDEX
    Explanations

    Negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     bluff
    -0.26
    åľ¨çº¿
    -0.26
     bright
    -0.25
     always
    -0.25
    åij½ä¸Ń
    -0.24
    ä½ľèĢħæľ¬äºº
    -0.24
     Always
    -0.24
     own
    -0.24
    åħīèį£
    -0.24
    æľ¬èº«å°±æĺ¯
    -0.24
    POSITIVE LOGITS
    ä¸įæĺ¯
    0.63
    ä¹Łä¸įæĺ¯
    0.57
    并éĿŀ
    0.57
    并ä¸įæĺ¯
    0.54
    éĥ½ä¸įæĺ¯
    0.54
    并ä¸į
    0.49
     nicht
    0.45
    è¿Ļä¸įæĺ¯
    0.44
     not
    0.43
    ä¸įæĺ¯ä¸Ģ个
    0.42
    Activations Density 0.001%

    No Known Activations