© 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. 129863
    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
    eg
    -0.28
     reversible
    -0.27
     reversed
    -0.27
    riad
    -0.26
    å¸ĤæĶ¿åįı
    -0.26
    ohana
    -0.25
    åĪĿ
    -0.25
    åѦéĻ¢
    -0.25
    obi
    -0.25
    åħĭåĪ¶
    -0.24
    POSITIVE LOGITS
    urance
    0.25
    twitter
    0.25
     sever
    0.24
    ừng
    0.24
     Cres
    0.24
    touch
    0.24
    çķĽ
    0.24
    resher
    0.24
     Keller
    0.23
    次è¦ģ
    0.23
    Activations Density 0.207%

    No Known Activations

    This feature has no known activations.