© 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. 106817
    Prev
    Next
    INDEX
    Explanations

    Code and technical text

    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
    çĿĢæīĭ
    -0.29
    sworth
    -0.27
    rcode
    -0.25
    ponsored
    -0.25
    -separated
    -0.24
    æīĢ
    -0.24
     Crow
    -0.24
    åŁİå¸Ĥ群
    -0.24
    izona
    -0.24
     horny
    -0.24
    POSITIVE LOGITS
    åĪ·æĸ°
    0.38
    æĽ´æĸ°
    0.36
    èĪĬ
    0.35
     updating
    0.33
     either
    0.33
    either
    0.32
     updates
    0.31
     update
    0.31
    æŧ
    0.31
    è¦ģä¹Ī
    0.31
    Activations Density 66.318%

    No Known Activations