© 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. 40891
    Prev
    Next
    INDEX
    Explanations

    translation

    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
    é£İ
    -0.29
     reels
    -0.28
    風
    -0.27
    åĵĹ
    -0.25
     Ley
    -0.25
    Ra
    -0.24
    ronic
    -0.24
    abit
    -0.24
    Ti
    -0.24
     Tit
    -0.24
    POSITIVE LOGITS
     translation
    0.38
     Translation
    0.37
     transl
    0.36
     basic
    0.36
     translating
    0.34
     translate
    0.33
     translated
    0.33
     fundamental
    0.33
    Translation
    0.32
    translation
    0.31
    Activations Density 0.004%

    No Known Activations