© 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. 130324
    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
    STER
    -0.31
    wort
    -0.28
    榷
    -0.26
     duplex
    -0.25
    quila
    -0.25
    uktur
    -0.25
     Sing
    -0.25
    rior
    -0.25
    tex
    -0.23
    acro
    -0.23
    POSITIVE LOGITS
    è¾Ļ
    0.29
    æĪijåİ»
    0.25
    çłģ
    0.24
     Assass
    0.24
     enlist
    0.24
    Brains
    0.24
     moz
    0.24
    ãĤĪãģĨ
    0.23
     unconditional
    0.23
     Neuroscience
    0.23
    Activations Density 1.754%

    No Known Activations

    This feature has no known activations.