© 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. 106841
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    oup
    -0.27
    ä»İä¸ļ
    -0.26
    roi
    -0.26
    istique
    -0.25
    Kn
    -0.25
    æĭīæĸ¯
    -0.25
    MODULE
    -0.24
    ä¸Ģ个éĹ®é¢ĺ
    -0.24
    LC
    -0.24
    ris
    -0.24
    POSITIVE LOGITS
    ä¸įæĺĵ
    0.27
    饱满
    0.27
    çĮ·
    0.26
     cul
    0.26
    ä¸į容æĺĵ
    0.25
    apol
    0.24
    åįıè°ĥåıijå±ķ
    0.24
     lor
    0.24
    ahead
    0.24
    Serialized
    0.23
    Activations Density 2.206%

    No Known Activations