© 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. 62997
    Prev
    Next
    INDEX
    Explanations

    .org

    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
    ä¾µçĬ¯
    -0.26
    主åĬ¨
    -0.26
    æ´»åĬ¨
    -0.26
    缩
    -0.25
    åħ¨éķĩ
    -0.25
     mas
    -0.25
    æīĢåľ¨
    -0.24
     THROW
    -0.24
    åĢĻéĢī人
    -0.24
     Mas
    -0.24
    POSITIVE LOGITS
    -che
    0.29
    è¿Ļå¥Ĺ
    0.26
    oodle
    0.25
     Kit
    0.25
     kit
    0.25
    ODO
    0.24
    erable
    0.24
     Fuse
    0.23
    ˣ
    0.23
    çļĦä¸ĢäºĽ
    0.23
    Activations Density 0.780%

    No Known Activations