© 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. 5025
    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
     brows
    -0.29
    çħŀ
    -0.27
    eos
    -0.27
    çķĻè¨ĢæĿ¿
    -0.27
    мÑĭ
    -0.26
    rends
    -0.25
    çĸ«
    -0.25
    aru
    -0.25
    ä¸Ĭè°ĥ
    -0.25
    çķ¥
    -0.25
    POSITIVE LOGITS
    icom
    0.27
    lical
    0.27
     unrealistic
    0.26
    ochrome
    0.26
    èħ¿
    0.26
    .Component
    0.26
    iba
    0.25
    ä¸įä¸ĭ
    0.25
    issan
    0.25
    ianne
    0.25
    Activations Density 1.280%

    No Known Activations

    This feature has no known activations.