© 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. 30-TRANSCODER-HP
    7. 96744
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    津贴
    -0.28
    indices
    -0.27
     fine
    -0.25
    åĨįåĪ°
    -0.24
    çĶŁäº§çĶŁæ´»
    -0.24
    ochen
    -0.24
    æķ´ä½ĵ
    -0.23
    _indices
    -0.23
    vi
    -0.23
    æīĢ说çļĦ
    -0.23
    POSITIVE LOGITS
    èµĦæĸĻæĺ¾ç¤º
    0.26
     elevator
    0.24
    女è£ħ
    0.24
    æĸ¹éĿ¢
    0.23
    éĽĨåĽ¢èĤ¡ä»½
    0.23
    åīįè¿Ľ
    0.23
    .del
    0.23
    车主
    0.23
    解åĨ³
    0.23
    bul
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.