© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88982
    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
    Negative Logits
    VED
    -0.28
    yl
    -0.26
    ÑĢова
    -0.26
    è¾IJ
    -0.26
    ConnectionString
    -0.26
    бли
    -0.25
     lif
    -0.24
    ()}}↵
    -0.24
    гад
    -0.24
    lington
    -0.23
    POSITIVE LOGITS
    atin
    0.28
    个人è§ĤçĤ¹
    0.27
    emachine
    0.27
    essage
    0.26
    rk
    0.26
    第ä¸Ģæī¹
    0.26
    æĹ¥è®¯
    0.25
    targets
    0.25
    æľįåĬ¡ä½ĵç³»
    0.24
    é¦ĸå±Ĭ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.