© 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. 98423
    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
    -colored
    -0.28
    驳
    -0.27
    åªĴ
    -0.26
    åıĸåĨ³äºİ
    -0.25
    (dep
    -0.23
    æ±Ń
    -0.23
    çĤ¹åĦ¿
    -0.23
    çħ¤
    -0.23
     discriminate
    -0.23
     debunk
    -0.23
    POSITIVE LOGITS
     AX
    0.32
    online
    0.30
     YT
    0.28
     GANG
    0.28
    aign
    0.26
    æľĢçĪ±
    0.24
     Ala
    0.24
    AXB
    0.24
     Infinite
    0.24
    åĨĮ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.