© 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. 5868
    Prev
    Next
    INDEX
    Explanations

    Common suffixes

    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
    çŃ¾
    -0.25
    illing
    -0.25
    лав
    -0.24
    åŀ«
    -0.24
    å¾ĭ
    -0.24
    éĢĨ
    -0.24
    EXPORT
    -0.23
    éĩı
    -0.23
    åŁİ
    -0.23
    确认
    -0.23
    POSITIVE LOGITS
    yles
    0.26
    sted
    0.25
     cheer
    0.24
     sout
    0.24
     XO
    0.23
    æijĩ头
    0.23
     fatally
    0.23
    uce
    0.23
     )[
    0.23
    sters
    0.23
    Activations Density 0.268%

    No Known Activations