© 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. 39532
    Prev
    Next
    INDEX
    Explanations

    Conjunctions, ramblings, and code

    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
    scoped
    -0.27
     scoped
    -0.26
     kr
    -0.25
     FO
    -0.24
     |↵↵
    -0.24
    ä¾ĭå¤ĸ
    -0.24
    çľ¼
    -0.24
    lops
    -0.24
    _UC
    -0.24
    èħ¹
    -0.24
    POSITIVE LOGITS
    _bridge
    0.28
    åŃ°
    0.27
    åIJĪä½ľåħ³ç³»
    0.25
    表çݰ为
    0.24
    ä¸ºä½ł
    0.24
    å©¢
    0.24
    æ´ģ
    0.24
    ãĤıãģĭãĤĭ
    0.24
     dziaÅĤania
    0.24
    è¿Ļæĸ¹éĿ¢
    0.24
    Activations Density 0.124%

    No Known Activations