© 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. 6333
    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
    éĻ¤å¤ĸ
    -0.28
    roring
    -0.28
    çħ¨
    -0.26
    ä¸įæĥ³
    -0.25
     RAT
    -0.25
    .dc
    -0.24
    è·¨è¶Ĭ
    -0.24
    æĥ³
    -0.24
    éĺ²çģ«
    -0.24
    ãģ¨ãģĵãĤįãģ§
    -0.24
    POSITIVE LOGITS
    åįģéĩĮ
    0.31
    omal
    0.29
    ·»
    0.27
    roller
    0.27
     dÆ°
    0.25
    oscope
    0.24
    iswa
    0.24
    çº
    0.24
    ipers
    0.23
    .restore
    0.23
    Activations Density 1.641%

    No Known Activations

    This feature has no known activations.