© 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. 6466
    Prev
    Next
    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    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
     scor
    -0.28
    讲è¯Ŀ
    -0.28
    reo
    -0.27
     backs
    -0.26
    ä¸įè¿ľ
    -0.25
     Cer
    -0.24
    çªĹåı£
    -0.24
    Unavailable
    -0.24
    cer
    -0.24
    æĭĵ
    -0.24
    POSITIVE LOGITS
    è¦ģä¸įè¦ģ
    0.39
     whether
    0.34
    whether
    0.34
    æĺ¯åIJ¦
    0.33
     пÑĢедлаг
    0.33
     proposed
    0.32
     æĺ¯åIJ¦
    0.30
     WHETHER
    0.30
     Whether
    0.30
     Suggestions
    0.29
    Activations Density 0.067%

    No Known Activations