© 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. 107144
    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
    ifndef
    -0.30
    strtotime
    -0.28
    æī©å®¹
    -0.27
    ä¸įä¸Ĭ
    -0.26
    ç»ĵ论
    -0.26
    产åĢ¼
    -0.25
    wä
    -0.24
    æĦŁåħ´è¶£
    -0.24
    -offset
    -0.24
     Zub
    -0.24
    POSITIVE LOGITS
     ÑģпÑĢав
    0.26
     Au
    0.26
    丼
    0.25
    Identification
    0.25
    çŃĴ
    0.24
    elled
    0.24
    asaki
    0.24
    пÑĥÑģк
    0.24
    å½Ĵå±ŀäºİ
    0.23
     YES
    0.23
    Activations Density 6.518%

    No Known Activations

    This feature has no known activations.