© 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. 41039
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    phants
    -0.26
    ihan
    -0.25
    icine
    -0.25
    åıijæİĺ
    -0.25
    izioni
    -0.24
    iamond
    -0.24
    éļ¾çĤ¹
    -0.23
    TestFixture
    -0.23
    -com
    -0.23
     Medicine
    -0.23
    POSITIVE LOGITS
    itos
    0.30
    çĥĤ
    0.26
    èµĦäº§è´ŁåĢº
    0.25
     costing
    0.25
     subordinate
    0.25
     blot
    0.25
    è²Ĥ
    0.24
    æıIJä¾Ľä¼ĺè´¨
    0.24
     Burb
    0.24
    亡
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.