© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 62853
    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
    blers
    -0.26
     material
    -0.26
    UDA
    -0.26
    æĸ°æĿIJæĸĻ
    -0.25
    rch
    -0.25
     spor
    -0.24
    armac
    -0.24
    æĦ«
    -0.24
    ottom
    -0.24
    顶å±Ĥ
    -0.24
    POSITIVE LOGITS
     Bre
    0.27
    antry
    0.26
    ~=
    0.25
    è¿Ľåİ»
    0.24
    Bre
    0.24
    ä½į
    0.23
     ani
    0.23
     Cy
    0.23
    ä¹³æĪ¿
    0.22
    大佬
    0.22
    Activations Density 23.083%

    No Known Activations

    This feature has no known activations.