© 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. 14-TRANSCODER-HP
    7. 39439
    Prev
    Next
    INDEX
    Explanations

    violence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iable
    -0.31
    omm
    -0.27
    icy
    -0.25
    æīĵæŃ»
    -0.25
    iad
    -0.25
    ivable
    -0.25
    æ»ĭ
    -0.25
     oneself
    -0.24
    rou
    -0.24
    ouce
    -0.24
    POSITIVE LOGITS
    æ°¸è¿ľ
    0.26
    èĥ¼
    0.25
    /stretchr
    0.24
    æĶ¹
    0.24
     Bow
    0.24
     Spotlight
    0.23
    _|
    0.23
    äºĨå¤ļå°ij
    0.23
    çį¾
    0.23
     ksztaÅĤ
    0.23
    Activations Density 0.053%

    No Known Activations