© 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. 20-TRANSCODER-HP
    7. 142545
    Prev
    Next
    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¸Ĥå§Ķ常å§Ķ
    -0.27
    toggle
    -0.25
    _chip
    -0.24
    å¸Ĥå§Ķ书记
    -0.24
    irtschaft
    -0.24
     facial
    -0.23
    vide
    -0.23
    æľ¨
    -0.23
    éŁ
    -0.23
    ):(
    -0.23
    POSITIVE LOGITS
    对åħ¶è¿Ľè¡Į
    0.30
    ifest
    0.26
    æľīæīĢä¸įåIJĮ
    0.26
    /DD
    0.24
    æľĪä¸ĭ
    0.24
     prog
    0.24
     XCT
    0.24
     pomp
    0.24
    .bc
    0.23
     Yad
    0.23
    Activations Density 10.698%

    No Known Activations