© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30312
    Prev
    Next
    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ilm
    -0.28
    主æµģ
    -0.25
     år
    -0.25
    æľ¬èº«å°±æĺ¯
    -0.24
    ASC
    -0.24
     forg
    -0.24
    ";}↵
    -0.24
    -provider
    -0.24
    å½ķåıĸ
    -0.24
    建设åĴĮ
    -0.24
    POSITIVE LOGITS
     Rep
    0.30
    Rep
    0.28
     اÙĦتج
    0.27
    åı«
    0.26
    éļľ
    0.25
    Over
    0.25
    åIJ¸åħ¥
    0.25
     Pull
    0.25
     neph
    0.24
     pull
    0.24
    Activations Density 1.053%

    No Known Activations