© 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. 32-TRANSCODER-HP
    7. 40864
    Prev
    Next
    INDEX
    Explanations

    technical documentation/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åģı
    -0.30
     zam
    -0.29
    write
    -0.28
    amil
    -0.27
    åįıè°ĥ
    -0.27
     write
    -0.27
    uckles
    -0.26
     Mayer
    -0.26
    apot
    -0.26
    ä¸ī家
    -0.26
    POSITIVE LOGITS
    æīģ
    0.28
    OTA
    0.26
    ain
    0.26
    âĻ¢
    0.26
    飽
    0.25
     random
    0.25
     interpre
    0.24
    è¯łéĩĬ
    0.24
     singles
    0.24
    æ§ł
    0.24
    Activations Density 0.052%

    No Known Activations