© 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. 31-TRANSCODER-HP
    7. 19766
    Prev
    Next
    INDEX
    Explanations

    Licenses and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Generate
    -0.30
    éģ´
    -0.30
    elu
    -0.28
    åıijçİ°äºĨ
    -0.27
    建ç«ĭäºĨ
    -0.26
     Calculate
    -0.26
    åŃĢ
    -0.26
    reation
    -0.25
     yaptıģı
    -0.25
    asso
    -0.25
    POSITIVE LOGITS
    å¾Ĺ
    0.95
    å¾ĹäºĨ
    0.73
    å¾ĹåĪ°
    0.72
    èİ·å¾Ĺ
    0.68
    èİ·
    0.61
     obt
    0.60
     ob
    0.58
    à¹Ħà¸Ķ
    0.56
     get
    0.56
    å¾Ĺ天
    0.56
    Activations Density 5.143%

    No Known Activations