© 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. 12-TRANSCODER-HP
    7. 23968
    Prev
    Next
    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å»ĵ
    -0.27
    toBeTruthy
    -0.26
     fulfill
    -0.26
     zost
    -0.26
    ather
    -0.25
    顺çĿĢ
    -0.24
    两æĿ¡
    -0.24
     wast
    -0.24
    å¤ĩ
    -0.24
    åıįåĢĴ
    -0.24
    POSITIVE LOGITS
    iles
    0.31
    -headed
    0.31
    pes
    0.27
    cu
    0.27
    yun
    0.26
    佶
    0.26
    liest
    0.25
    ysts
    0.25
    ıld
    0.25
    reas
    0.24
    Activations Density 0.008%

    No Known Activations