© 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. 23-TRANSCODER-HP
    7. 25611
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    blocking
    -0.26
    atro
    -0.26
    velle
    -0.25
    inois
    -0.25
    é«ĺå±Ĥ次
    -0.25
    вл
    -0.24
    æİıåĩº
    -0.24
     micron
    -0.24
    erman
    -0.24
    IRO
    -0.24
    POSITIVE LOGITS
    ï¼Ł”
    0.27
     RELEASE
    0.26
    ?”
    0.26
    æīĢè°ĵ
    0.26
     PURPOSE
    0.25
    lang
    0.25
    âĢ¦”
    0.24
     Negot
    0.24
     thả
    0.24
    éĩĬæĶ¾
    0.24
    Activations Density 0.003%

    No Known Activations