© 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. 130554
    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
    躲
    -0.27
    éĩįçĤ¹é¢ĨåŁŁ
    -0.26
    emap
    -0.25
    efault
    -0.24
    rias
    -0.22
    å¾ĹäºĨ
    -0.22
    æĺ¯ä¸Ģ款
    -0.22
     Coal
    -0.22
    éĥ¨éķ¿
    -0.22
     Hab
    -0.22
    POSITIVE LOGITS
    اغ
    0.26
     predecessors
    0.25
    ians
    0.24
     race
    0.24
    Me
    0.23
    regor
    0.23
     Me
    0.23
     vulnerability
    0.23
     fortunes
    0.23
    Bush
    0.23
    Activations Density 20.687%

    No Known Activations

    This feature has no known activations.