© 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. 64859
    Prev
    Next
    INDEX
    Explanations

    :

    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
    çľĭçľĭ
    -0.27
    rende
    -0.27
    atee
    -0.25
    ãĤ¾
    -0.25
    ders
    -0.24
    estination
    -0.24
    destination
    -0.23
    yster
    -0.23
    ington
    -0.23
    å¼ĢåıijåķĨ
    -0.23
    POSITIVE LOGITS
    åĬ©
    0.25
    èĭĦ
    0.25
    è¡¥
    0.24
    REW
    0.23
    æļ´éľ²
    0.23
     Brother
    0.23
    åı£
    0.23
     cues
    0.23
    交
    0.23
    :false
    0.23
    Activations Density 8.586%

    No Known Activations