© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5811
    Prev
    Next
    INDEX
    Explanations

    metabolic syndrome

    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
    壯
    -0.27
    PRINTF
    -0.26
    ä»»
    -0.26
    大ãģįãģĦ
    -0.25
    annes
    -0.24
    ä¸Ĭãģ§
    -0.24
     Infantry
    -0.24
    ace
    -0.24
    çļĦä¹łæĥ¯
    -0.24
    çľ¼éĩĮ
    -0.24
    POSITIVE LOGITS
    缮å½ķ
    0.27
    cher
    0.27
    夹
    0.26
    å±ĭ
    0.26
    pir
    0.26
    åıĪä¸Ģ次
    0.25
    res
    0.25
    éĻ¤
    0.25
    &&
    0.24
    M
    0.24
    Activations Density 0.097%

    No Known Activations