© 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. 98092
    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
     chambers
    -0.24
    å¸ĤæĶ¿åºľ
    -0.24
    ä¸ĵ项è¡ĮåĬ¨
    -0.24
     Spectrum
    -0.23
    ä¸įå¼Ģ
    -0.23
    etta
    -0.23
    icht
    -0.23
    æĦıèŃĺ
    -0.23
    Glass
    -0.23
    æīįå¹²
    -0.22
    POSITIVE LOGITS
    maal
    0.26
     follower
    0.23
    ucs
    0.23
    unt
    0.22
    imal
    0.22
    æºIJ
    0.22
     northwest
    0.21
    æĪªåĽ¾
    0.21
     ""){↵
    0.21
    acente
    0.21
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.