© 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. 40836
    Prev
    Next
    INDEX
    Explanations

    Malaysia locations

    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
     Chu
    -0.28
    æĹ¥çĶµ
    -0.28
    uhan
    -0.28
    head
    -0.27
    esso
    -0.26
     cheek
    -0.26
     TOK
    -0.26
    å°ıåIJĥ
    -0.26
    Han
    -0.25
    allah
    -0.25
    POSITIVE LOGITS
    çĻ
    0.30
    æİĸ
    0.26
    æµĨ
    0.26
    umbling
    0.25
    Gl
    0.24
     Wit
    0.23
    纤维
    0.23
    ä¿Ŀ温
    0.23
    agnost
    0.23
    oder
    0.23
    Activations Density 0.013%

    No Known Activations