© 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. 140780
    Prev
    Next
    INDEX
    Explanations

    long technical descriptions

    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
    omi
    -0.28
    说æĺİ
    -0.27
    .break
    -0.25
    resher
    -0.25
    Forge
    -0.24
    _mime
    -0.24
    .newaxis
    -0.24
    =-=-=-=-=-=-=-=-
    -0.24
    ä¸ŃéĢĶ
    -0.24
    ç»Ħ
    -0.24
    POSITIVE LOGITS
    åľ¨ä»ĸçļĦ
    0.30
    对该
    0.25
    ths
    0.25
    ssa
    0.25
    级以ä¸Ĭ
    0.25
    éģģ
    0.24
     Buk
    0.24
    ä¼ļéĢīæĭ©
    0.24
    éļı便
    0.24
    lk
    0.24
    Activations Density 4.396%

    No Known Activations