© 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. 5181
    Prev
    Next
    INDEX
    Explanations

    Age

    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
    ä¸Ĭ线
    -0.29
    缸åħ³çļĦ
    -0.27
    è¯ģ书
    -0.27
    责任人
    -0.26
    umbing
    -0.26
    -lined
    -0.25
    erator
    -0.25
    sheet
    -0.24
    dre
    -0.24
     defender
    -0.23
    POSITIVE LOGITS
    concert
    0.28
    avers
    0.27
     enrich
    0.27
    uent
    0.25
    Ã¼ÅŁ
    0.24
     Bayer
    0.24
    å¾Ļ
    0.24
    ACHI
    0.24
    arters
    0.24
     soit
    0.23
    Activations Density 0.049%

    No Known Activations