© 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. 108614
    Prev
    Next
    INDEX
    Explanations

    software application issues

    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
    åįķçĭ¬
    -0.40
     independently
    -0.39
     unrelated
    -0.39
     Independ
    -0.39
    çĭ¬ç«ĭ
    -0.38
    éĢļçĶ¨
    -0.38
     standalone
    -0.37
     other
    -0.36
    åħ¶ä»ĸ
    -0.35
     outside
    -0.35
    POSITIVE LOGITS
    igi
    0.26
    渺
    0.25
    uliar
    0.25
    æ¸IJ
    0.25
    æĻļ
    0.25
    egan
    0.24
    vf
    0.24
    寵
    0.24
    esian
    0.24
     updater
    0.24
    Activations Density 60.166%

    No Known Activations