© 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. 97693
    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
    家åĬ¡
    -0.26
    çĨ
    -0.26
    综åIJĪä½ĵ
    -0.25
    åŃ¦ä¹łæĪIJ绩
    -0.25
    å±Ĥåĩº
    -0.25
    scriptId
    -0.24
    空æ°ĶåĩĢåĮĸ
    -0.24
    ä¸Ģä½ĵ
    -0.24
    æĸ°åĨłçĸ«æĥħ
    -0.24
    åĢ¼å¾Ĺåħ³æ³¨
    -0.24
    POSITIVE LOGITS
    åij½
    0.30
     cons
    0.26
     distributed
    0.25
    å·®
    0.24
    ä½ķ
    0.24
    ä¼łæĿ¥
    0.24
    com
    0.24
    åĩĨ
    0.24
     //$
    0.23
    -cons
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.