© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5032
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    欢è¿İ大家
    -0.28
     Hoover
    -0.26
    _CLAMP
    -0.25
     Trafford
    -0.25
    LoginPage
    -0.25
    Enlarge
    -0.25
    [position
    -0.25
    åIJĦé¡¹å·¥ä½ľ
    -0.24
    æľīè¿ĩ
    -0.24
    ror
    -0.23
    POSITIVE LOGITS
    æĿIJ
    0.28
    ëŁ½
    0.26
    disc
    0.25
     ther
    0.24
    æŶéĹ´åĨħ
    0.24
    è¿ĺ
    0.24
    ä¸įåı¯
    0.24
    Disc
    0.24
    .Inject
    0.24
    itating
    0.23
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.