© 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. 108677
    Prev
    Next
    INDEX
    Explanations

    programming questions

    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
    _UNUSED
    -0.29
    èĴ¿
    -0.28
    waves
    -0.26
    çľĭä¸Ģä¸ĭ
    -0.26
    å±ķå¼Ģ
    -0.25
     Matth
    -0.25
    getAs
    -0.25
     никак
    -0.24
    tml
    -0.24
    ë¶ĵ
    -0.24
    POSITIVE LOGITS
    æĬĢæľ¯åĴĮ
    0.27
    eton
    0.27
    æķ´æ²»
    0.24
     Báo
    0.24
    Node
    0.24
    ä¿¡æīĺ
    0.23
    çĶŁäº§åĴĮ
    0.23
     innovate
    0.23
     cac
    0.23
    åľ¨éĤ£éĩĮ
    0.23
    Activations Density 28.274%

    No Known Activations