© 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. 6122
    Prev
    Next
    INDEX
    Explanations

    technical conversations

    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
    oms
    -0.28
    å¥ĩèij©
    -0.28
    iat
    -0.27
    stem
    -0.27
    led
    -0.26
     suck
    -0.25
    çļĦéľĢæ±Ĥ
    -0.25
    åĿ¨
    -0.25
     historically
    -0.25
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.25
    POSITIVE LOGITS
    å·²ç»ıå¼Ģå§ĭ
    0.27
    侵害
    0.27
    Serviço
    0.26
     invaded
    0.26
    被æĬĵ
    0.26
    .assignment
    0.25
    éģIJ
    0.25
    åĬ«
    0.25
    个人è§ĤçĤ¹
    0.25
     длиÑĤелÑĮн
    0.24
    Activations Density 0.008%

    No Known Activations