© 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. 30212
    Prev
    Next
    INDEX
    Explanations

    polls

    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
    _,↵
    -0.29
    -door
    -0.26
    -Clause
    -0.25
    eyJ
    -0.25
    legant
    -0.25
    çı£
    -0.25
     AJAX
    -0.25
     Shin
    -0.24
    åħ¥ä¾µ
    -0.24
     dine
    -0.24
    POSITIVE LOGITS
    é«ĺ度éĩįè§Ĩ
    0.28
     Trust
    0.27
     vers
    0.27
    æĴŃ
    0.26
    积累äºĨ
    0.26
    OD
    0.26
    .record
    0.25
     cũ
    0.24
    icher
    0.23
    .box
    0.23
    Activations Density 0.133%

    No Known Activations