© 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. 129811
    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
    WithContext
    -0.27
    å½»
    -0.27
    Solo
    -0.27
     centr
    -0.26
     suit
    -0.26
    ettel
    -0.26
    èŀįåħ¥
    -0.25
    loating
    -0.25
    éĸ£
    -0.24
     Solo
    -0.24
    POSITIVE LOGITS
    ELY
    0.28
    -bound
    0.26
    Ùħار
    0.25
    æŁIJ
    0.25
    isure
    0.25
    ãĥ©ãĥ³ãĤ¹
    0.24
    ãĤĪãģĨãģ§
    0.24
     sure
    0.24
    roit
    0.24
    tsy
    0.24
    Activations Density 9.259%

    No Known Activations

    This feature has no known activations.