© 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. 141936
    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
    rium
    -0.31
    /misc
    -0.27
    åı¯ä»¥çľĭåĪ°
    -0.24
    ych
    -0.24
    ä¿¡
    -0.24
     iterable
    -0.24
    Height
    -0.24
    AMP
    -0.24
    Armor
    -0.23
    /course
    -0.23
    POSITIVE LOGITS
    eyed
    0.27
    dzi
    0.26
    çĿij
    0.25
    åı¸
    0.25
    prt
    0.25
    typename
    0.24
    丧失
    0.24
    çļĦæĥħ绪
    0.24
    æĸij
    0.24
    åĪĴ
    0.23
    Activations Density 2.619%

    No Known Activations

    This feature has no known activations.