© 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. 142357
    Prev
    Next
    INDEX
    Explanations

    Parenthesis

    np_max-act · gemini-2.0-flash
    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
    çī¹æ´¾
    -0.31
    æĦı大
    -0.27
    ).\
    -0.26
    ä¼ļéķ¿
    -0.25
     surv
    -0.24
    éķĵ
    -0.24
    ëĦIJ
    -0.24
    èĢĥ
    -0.24
    rev
    -0.24
     arch
    -0.24
    POSITIVE LOGITS
    ä»»
    0.31
    .shtml
    0.28
    åı¯èĥ½ãģ§ãģĻ
    0.28
    راع
    0.27
     Tomb
    0.26
    è¿ĻæŶåĢĻ
    0.26
    åĬ¨æijĩ
    0.26
    æĮĸ
    0.26
    æѤæŶ
    0.24
    opo
    0.24
    Activations Density 1.074%

    No Known Activations