© 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. 6159
    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
    æĿ¥è®²
    -0.27
    faf
    -0.27
     fi
    -0.27
    _dot
    -0.25
    åĴĮ个人
    -0.25
    è¯ķ
    -0.25
    Ev
    -0.24
    èĢĮè¨Ģ
    -0.24
     attempt
    -0.23
     shall
    -0.23
    POSITIVE LOGITS
    kok
    0.28
    zee
    0.27
    级以ä¸Ĭ
    0.26
    å²Ľä¸Ĭ
    0.26
    ç°ĩ
    0.26
     authDomain
    0.25
     mast
    0.25
    eree
    0.25
    кÑĥ
    0.24
     Kok
    0.24
    Activations Density 1.694%

    No Known Activations

    This feature has no known activations.