© 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. 56599
    Prev
    Next
    INDEX
    Explanations

    violence

    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
    -Compatible
    -0.27
    è¯Ŀ说
    -0.25
    .Rendering
    -0.25
    _PREF
    -0.24
    æĦ¿
    -0.24
     hen
    -0.24
     baz
    -0.24
    ORIZ
    -0.24
    !("{}",
    -0.23
    .parts
    -0.23
    POSITIVE LOGITS
    é½IJ
    0.32
    纷纷
    0.31
     altern
    0.29
    ä¸įæĸŃåıijå±ķ
    0.29
    è¿Ń
    0.29
    æѦåĬŁ
    0.27
    åIJĦèĩª
    0.26
    æĭĬ
    0.26
    é½Ĭ
    0.26
    uali
    0.25
    Activations Density 0.002%

    No Known Activations