© 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. 5344
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
     Lamb
    -0.25
    æĵį
    -0.25
     Graz
    -0.24
    æŧ
    -0.23
    yük
    -0.23
    (operation
    -0.23
    worth
    -0.23
    æĢį
    -0.23
    ä¸Ģè¡Į
    -0.23
    strings
    -0.22
    POSITIVE LOGITS
    multiply
    0.28
     Team
    0.27
    inality
    0.27
    æĸ¼æĺ¯
    0.25
    为ä¹ĭ
    0.25
    让人们
    0.25
    åĸ±
    0.24
    让å®ĥ
    0.24
    äºİæĺ¯
    0.23
     vagy
    0.23
    Activations Density 0.055%

    No Known Activations