© 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. 107713
    Prev
    Next
    INDEX
    Explanations

    Body parts

    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
    ami
    -0.28
    彩
    -0.26
    宪
    -0.26
    åĵ¨
    -0.25
    ç§Ģ
    -0.25
    ///<
    -0.25
    åĩī
    -0.25
    çļĤ
    -0.24
    çļĦåĨħ容
    -0.24
    rans
    -0.24
    POSITIVE LOGITS
    ailles
    0.29
    é³ħ
    0.29
    robot
    0.28
    EXTERNAL
    0.27
    icias
    0.26
    çĩİ
    0.26
    Robot
    0.25
    .addProperty
    0.25
     Automation
    0.25
     automation
    0.25
    Activations Density 2.222%

    No Known Activations