© 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. 22-TRANSCODER-HP
    7. 99150
    Prev
    Next
    INDEX
    Explanations

    informal online posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĬ«
    -0.30
    é»ı
    -0.27
     DECL
    -0.26
    èIJ½
    -0.26
    æ¡Ĩæŀ¶
    -0.26
    交
    -0.26
    å°ij
    -0.25
     nhấn
    -0.25
    å¹²é¢Ħ
    -0.24
    æŃ¢
    -0.24
    POSITIVE LOGITS
     sourceMapping
    0.29
    ç²¾çĽĬæ±Ĥç²¾
    0.25
    åıijæī¬
    0.25
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.25
    asia
    0.24
    itor
    0.24
    èĢģå¸ĪçļĦ
    0.24
     UserDao
    0.24
     },↵↵↵
    0.24
    enville
    0.23
    Activations Density 0.006%

    No Known Activations