© 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. 87160
    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
     codes
    -0.28
     Codes
    -0.26
    â¼
    -0.26
     universal
    -0.25
    çľģæĶ¿åºľ
    -0.25
     permanent
    -0.25
    åı¯éĿłçļĦ
    -0.24
     microwave
    -0.24
    æĩĤ
    -0.24
     proto
    -0.24
    POSITIVE LOGITS
    hum
    0.31
    eut
    0.26
    湿度
    0.26
    Hum
    0.25
    éĴĪ
    0.24
    humidity
    0.24
     MD
    0.23
    æ£ĺ
    0.23
    æĥ³è±¡
    0.23
    mdi
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.