© 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. 22-TRANSCODER-HP
    7. 99056
    Prev
    Next
    INDEX
    Explanations

    Code and technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĬ
    -0.25
    rent
    -0.24
    åħħåĪĨåĪ©çĶ¨
    -0.24
    ufen
    -0.24
    æľīçĽĬ
    -0.24
    å§IJ妹
    -0.24
     linked
    -0.23
    /effects
    -0.23
    cono
    -0.23
    insky
    -0.23
    POSITIVE LOGITS
    åij½åIJį为
    0.31
    称为
    0.30
    称
    0.30
    ç®Ģ称
    0.30
    称ä¹ĭ为
    0.30
    称åij¼
    0.29
    称ä¹ĭ
    0.29
    æĪIJ为
    0.29
    泪
    0.29
    ç¼ĸåı·
    0.28
    Activations Density 0.004%

    No Known Activations