© 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. 40940
    Prev
    Next
    INDEX
    Explanations

    geographic 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
     itr
    -0.27
    itary
    -0.26
    itr
    -0.26
    -Jul
    -0.25
    Engine
    -0.25
    éĢĨ
    -0.24
    rell
    -0.24
     Vers
    -0.24
    æł¼
    -0.24
    unit
    -0.24
    POSITIVE LOGITS
    (io
    0.28
    å¼¼
    0.28
    åįģåŃĹ
    0.27
    acula
    0.26
    NU
    0.26
    Sw
    0.25
    Nu
    0.25
    DAC
    0.24
     cái
    0.24
    欢è¿İæĤ¨
    0.24
    Activations Density 0.002%

    No Known Activations