© 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. 63996
    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
    llx
    -0.29
    uss
    -0.26
    arb
    -0.26
    ãĤıãģij
    -0.26
    akes
    -0.25
    对ä¼ģä¸ļ
    -0.24
    欺
    -0.24
    imited
    -0.24
    asset
    -0.23
    çĩĥæ²¹
    -0.23
    POSITIVE LOGITS
    åı¦ä¸Ģ个
    0.32
    åı¦ä¸Ģç§į
    0.29
    åı¦ä¸Ģ
    0.28
    åı¦ä¸Ģä½į
    0.26
    åIJĽåŃIJ
    0.26
     Ames
    0.26
    iris
    0.26
     another
    0.25
    åı¦å¤ĸä¸Ģ个
    0.25
    ContextHolder
    0.25
    Activations Density 29.872%

    No Known Activations

    This feature has no known activations.