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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7490
    Prev
    Next
    INDEX
    Explanations

    Licenses and code

    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
    ede
    -0.26
    éĽ¢ãĤĮ
    -0.25
     szcz
    -0.25
    ither
    -0.24
    aces
    -0.24
    æĿŁ
    -0.24
    utters
    -0.24
    æīĵçĮİ
    -0.24
    ushman
    -0.24
    sizei
    -0.23
    POSITIVE LOGITS
    ãģ®æĸ¹
    0.27
    åĵĪ
    0.27
    å¥
    0.26
     Efficient
    0.26
    纳
    0.25
    åĪĽæĸ°é©±åĬ¨
    0.25
     efficient
    0.24
    âĦħ
    0.24
    éĤ£ä¹Īç®Ģåįķ
    0.24
     Preferred
    0.24
    Activations Density 1.627%

    No Known Activations