© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63479
    Prev
    Next
    INDEX
    Explanations

    Esophageal fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raids
    -0.28
     uncomment
    -0.26
    ä»»
    -0.26
     neighbours
    -0.26
    antar
    -0.25
    人éĢł
    -0.25
    ä¾µæĿĥ
    -0.24
     interceptions
    -0.23
    itous
    -0.23
    esk
    -0.23
    POSITIVE LOGITS
    –↵↵
    0.29
    ä¸įä»ħè¦ģ
    0.28
     direction
    0.26
    æĸŁ
    0.25
    ä¸ĭ车
    0.25
    hausen
    0.25
    éĢ¢
    0.24
     Bü
    0.24
    åłĤ
    0.24
    UTION
    0.24
    Activations Density 1.620%

    No Known Activations