© 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. 18-TRANSCODER-HP
    7. 90083
    Prev
    Next
    INDEX
    Explanations

    Cleanliness and sanitization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rowave
    -0.26
    [right
    -0.26
    ilon
    -0.26
    غÙĪ
    -0.26
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.26
     [~,
    -0.25
    诱人
    -0.25
    åī§æľ¬
    -0.25
    cene
    -0.25
    ContentLoaded
    -0.25
    POSITIVE LOGITS
    ä¸Ģç»ı
    0.28
    zz
    0.27
    fd
    0.27
    æĪij们å¿ħé¡»
    0.27
    ve
    0.27
     ve
    0.27
    ves
    0.26
    èĴĹ
    0.26
    VE
    0.26
    æ»ŀ
    0.26
    Activations Density 7.803%

    No Known Activations