© 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. 130650
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĶ¾
    -0.27
    äºĮ级
    -0.27
    解
    -0.27
    <Func
    -0.27
    awan
    -0.26
    éļ¾
    -0.26
    Behavior
    -0.25
    .Drawing
    -0.25
     ext
    -0.25
    è¡Į
    -0.25
    POSITIVE LOGITS
     (£
    0.27
    NZ
    0.24
     Naj
    0.24
    åıĮåıĮ
    0.24
    è¯ģçĽij
    0.24
    :init
    0.24
    ä¹ĭ称
    0.24
    ä¼ļåIJĮ
    0.24
    äºĨä¸Ģ份
    0.24
    è¿Ļ两
    0.23
    Activations Density 1.638%

    No Known Activations

    This feature has no known activations.