© 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. 140665
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
    .instant
    -0.26
    acci
    -0.26
    isma
    -0.25
     Resume
    -0.25
    ä¸Ģ线
    -0.25
    æķijåij½
    -0.25
    æķijæµİ
    -0.24
    æį·
    -0.24
    джеÑĢ
    -0.24
    schlä
    -0.24
    POSITIVE LOGITS
    éĹ²ç½®
    0.45
    åºŁå¼ĥ
    0.41
     unused
    0.38
    Unused
    0.38
    _unused
    0.37
     Unused
    0.33
     abandoned
    0.33
    æĹłäºº
    0.33
    空
    0.33
    å¼ĥ
    0.33
    Activations Density 76.304%

    No Known Activations