© 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. 30-TRANSCODER-HP
    7. 96958
    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
    Negative Logits
     peeled
    -0.28
    hil
    -0.28
    Investigators
    -0.26
    æµħ
    -0.25
     deeper
    -0.25
    stem
    -0.24
     Shen
    -0.24
    浦
    -0.24
     sharper
    -0.23
    cido
    -0.23
    POSITIVE LOGITS
    注åħ¥
    0.28
    éĻ·éĺ±
    0.26
     madness
    0.26
    éĶ¹
    0.25
    sez
    0.25
    ForResource
    0.24
    è¾Ķ
    0.24
    é¢ļ
    0.24
    è¾ķ
    0.24
    ç»ijå®ļ
    0.24
    Activations Density 0.882%

    No Known Activations