© 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. 130191
    Prev
    Next
    INDEX
    Explanations

    9

    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
    è¿ĩ
    -0.28
    pipe
    -0.27
    jamin
    -0.26
    è¿Ļå°±æĺ¯
    -0.25
    orge
    -0.25
    åı¤ä»Ĭ
    -0.25
    罩
    -0.25
     choice
    -0.25
    ä¸īåĽĽ
    -0.25
     Squad
    -0.25
    POSITIVE LOGITS
     Trials
    0.29
    fers
    0.28
    åı³ä¾§
    0.26
     <<-
    0.25
     DIRECT
    0.25
    ä¸į代表
    0.25
    azes
    0.25
    trees
    0.25
     EVT
    0.24
    \Builder
    0.24
    Activations Density 7.607%

    No Known Activations