© 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. 129938
    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
    ä¸ĢèĪ¬æĺ¯
    -0.29
     incons
    -0.25
    ï¼Įé»ĺ认
    -0.24
    arch
    -0.24
    åİŁåŀĭ
    -0.24
    {:
    -0.23
    raw
    -0.23
     Won
    -0.23
    Bundle
    -0.23
    å²Ķ
    -0.23
    POSITIVE LOGITS
    她说
    0.29
    .lists
    0.27
    iu
    0.26
     Ferd
    0.26
     acquisitions
    0.24
    å±ħ
    0.24
     Budapest
    0.24
    æĶ¯éĺŁ
    0.24
     //------------------------------------------------
    0.23
     Resident
    0.23
    Activations Density 2.148%

    No Known Activations

    This feature has no known activations.