© 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. 44183
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     tr
    -0.37
     District
    -0.28
     Authors
    -0.27
    ĥģ
    -0.27
     mitigation
    -0.27
    å¿ĥ头
    -0.26
    åıĺçİ°
    -0.26
    èĥ¸åı£
    -0.26
    )&&
    -0.26
    .pk
    -0.26
    POSITIVE LOGITS
    /favicon
    0.27
    coop
    0.26
    å¿Į
    0.25
    èĶļ
    0.25
    elles
    0.25
    æĿĢäºĨ
    0.24
    aille
    0.24
     nik
    0.24
    ugg
    0.24
    олÑĮз
    0.24
    Activations Density 0.000%

    No Known Activations