© 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. 87736
    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
    åĶĩ
    -0.28
     Erin
    -0.24
     anche
    -0.24
    ä¹Łå°Ĩ
    -0.24
    _lit
    -0.24
    æīĢæıIJä¾Ľ
    -0.23
    è¯ŀ
    -0.23
     accustomed
    -0.23
    æĭ±
    -0.23
     angi
    -0.22
    POSITIVE LOGITS
    ä¸ĢæŦ
    0.29
     Sandwich
    0.26
    éºĴéºŁ
    0.25
    个交æĺĵ
    0.25
    INGTON
    0.25
    =~
    0.25
    ãĥ¯ãĤ¤
    0.25
    éļIJèĹı
    0.24
    èĸľ
    0.24
    ington
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.