© 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. 22-TRANSCODER-HP
    7. 98839
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phabet
    -0.34
    é³ĸ
    -0.27
    olan
    -0.26
    caling
    -0.24
    egative
    -0.24
    æ¯Ľ
    -0.24
    åīįè¿Ľ
    -0.24
    chant
    -0.24
    eprom
    -0.24
    each
    -0.24
    POSITIVE LOGITS
    åIJ¬äºĨ
    0.29
    arness
    0.26
    isko
    0.26
    æĴij
    0.25
     Spring
    0.25
    åĬ©çIJĨ
    0.25
    ä¸ī项
    0.24
    æ³Ħæ¼ı
    0.24
    åij¨ä¸ī
    0.24
    详解
    0.24
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.