© 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. 107397
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ¢ģ
    -0.31
    æĦģ
    -0.29
    åħī
    -0.29
    åıįæĺł
    -0.29
    ç»ĵåIJĪ
    -0.28
    äºij
    -0.27
    对æ¯Ķ
    -0.27
    æIJĢ
    -0.27
    以
    -0.27
    åįĬ
    -0.27
    POSITIVE LOGITS
     destiny
    0.29
    hwnd
    0.29
    äºĨä»ĸçļĦ
    0.27
    .Sin
    0.27
    ONO
    0.26
    é²Ł
    0.26
    çī¹æ´¾
    0.25
     ON
    0.25
    utom
    0.25
    erton
    0.24
    Activations Density 63.537%

    No Known Activations

    This feature has no known activations.