© 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. 40812
    Prev
    Next
    INDEX
    Explanations

    non-English tokens

    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
     parted
    -0.27
    енн
    -0.27
    _ATTRIB
    -0.26
    ungle
    -0.25
    仪åĻ¨
    -0.25
    enting
    -0.25
    ENTS
    -0.25
    EN
    -0.25
     En
    -0.24
     es
    -0.24
    POSITIVE LOGITS
    çĽ²
    0.27
    acin
    0.25
    éĥ¾
    0.25
    æħ¢
    0.25
    amel
    0.24
    ãĥ©ãĥ³ãĤ¹
    0.24
    é«ĺæ°´å¹³
    0.23
    GENCY
    0.23
    %C
    0.23
    俯
    0.23
    Activations Density 0.001%

    No Known Activations