© 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. 107111
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
     diagonal
    -0.29
    exual
    -0.27
    åĩ¡
    -0.27
    late
    -0.25
    æĪĸå¤ļ
    -0.25
    anol
    -0.25
    opard
    -0.24
    对åѦçĶŁ
    -0.24
    迳
    -0.24
     addAction
    -0.23
    POSITIVE LOGITS
    缩å°ı
    0.27
    ührung
    0.25
    Indeed
    0.24
     lifted
    0.24
     indeed
    0.24
    iser
    0.24
    ifying
    0.24
    éħª
    0.23
    isas
    0.23
    èµ·æĿ¥äºĨ
    0.23
    Activations Density 3.704%

    No Known Activations