© 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. 41761
    Prev
    Next
    INDEX
    Explanations

    security incidents

    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
     safety
    -0.27
     exceeded
    -0.26
    ware
    -0.26
     homicides
    -0.26
     Emer
    -0.25
    (course
    -0.25
    -multi
    -0.25
    atement
    -0.25
     prot
    -0.25
     course
    -0.24
    POSITIVE LOGITS
    chner
    0.27
    å¾Ĺä¸įåĪ°
    0.27
    顺
    0.26
     peel
    0.25
    书ä¸Ń
    0.25
     isi
    0.24
    åģĩ
    0.24
    isi
    0.24
    èĤī
    0.24
    è°·
    0.24
    Activations Density 0.215%

    No Known Activations