© 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. 14-TRANSCODER-HP
    7. 39605
    Prev
    Next
    INDEX
    Explanations

    citizen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    轩
    -0.26
     appName
    -0.25
     sting
    -0.25
    éķ¿å¤§
    -0.25
    inel
    -0.25
    .pointer
    -0.25
    tÃŃ
    -0.25
    .fil
    -0.24
    ech
    -0.24
    人æŃ»äº¡
    -0.24
    POSITIVE LOGITS
    abbo
    0.30
    åĮ¿åIJį
    0.27
    å®Į
    0.26
    åĪĨåĮĸ
    0.25
    ä»ĸ们
    0.25
    -tm
    0.25
    ä½ĨæĪij
    0.25
     sắc
    0.24
    åĪ®
    0.24
    spir
    0.24
    Activations Density 1.940%

    No Known Activations