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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6804
    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
    á»ıi
    -0.27
    ä¸ĭè°ĥ
    -0.26
     Train
    -0.25
    åĬŀ好
    -0.25
    åīįèĢħ
    -0.25
    èĢĮè¨Ģ
    -0.25
    è¿Ļ两个
    -0.25
     طرÙĬÙĤ
    -0.25
    Ãłn
    -0.24
     Impress
    -0.24
    POSITIVE LOGITS
    (AF
    0.27
     normally
    0.26
    .af
    0.25
     Horton
    0.25
    .AF
    0.25
    _CF
    0.25
    _DF
    0.25
    çĸ£
    0.24
     pand
    0.23
     CF
    0.23
    Activations Density 4.635%

    No Known Activations

    This feature has no known activations.