© 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. 9-TRANSCODER-HP
    7. 29108
    Prev
    Next
    INDEX
    Explanations

    git branch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¿Ļ家
    -0.29
    æĽ´è¦ģ
    -0.28
    PTS
    -0.28
    ä¸Ģ家
    -0.28
     Harvest
    -0.27
    OSH
    -0.27
    æŁĶ
    -0.27
    omics
    -0.27
     vari
    -0.27
    宫
    -0.26
    POSITIVE LOGITS
    tics
    0.29
    iration
    0.28
    taire
    0.25
     nug
    0.24
    sink
    0.24
    ëĿ½
    0.24
    æŃ¢ãĤģ
    0.24
     wipes
    0.24
    æĮģä¹ħ
    0.24
    tery
    0.24
    Activations Density 0.376%

    No Known Activations