© 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. 14-TRANSCODER-HP
    7. 41755
    Prev
    Next
    INDEX
    Explanations

    electronics and retail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åħŃåIJĪ
    -0.29
     tet
    -0.26
    çĦī
    -0.23
     :=↵
    -0.23
    IsActive
    -0.23
    æ´»
    -0.23
     Imports
    -0.23
    aÄĩ
    -0.22
    +f
    -0.22
     oma
    -0.21
    POSITIVE LOGITS
    ç¨Ģ
    0.34
    enance
    0.27
    ä¿©
    0.26
    æĬ¥éħ¬
    0.25
    ãģ¾ãģĹãģ¦
    0.24
    gun
    0.24
    ä¸ĢçĤ¹åĦ¿
    0.24
    htable
    0.24
    berman
    0.24
    è´¨éĩı
    0.23
    Activations Density 1.454%

    No Known Activations