© 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. 63005
    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
    BEL
    -0.27
     Bel
    -0.27
    iage
    -0.25
    鹤
    -0.25
    èµ·
    -0.25
    ará
    -0.25
     thu
    -0.25
    äche
    -0.25
     \↵↵
    -0.24
    Bel
    -0.24
    POSITIVE LOGITS
    liest
    0.29
    æĽ´å¥½
    0.25
    åĿļæŀľ
    0.25
    ankind
    0.24
    pip
    0.24
    ết
    0.24
    ãĥľãĥ¼
    0.24
    ands
    0.24
    -bound
    0.24
     Continental
    0.24
    Activations Density 1.514%

    No Known Activations

    This feature has no known activations.