© 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. 88377
    Prev
    Next
    INDEX
    Explanations

    immunodeficiency

    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
    表彰
    -0.30
    _pen
    -0.27
     Gü
    -0.26
    statt
    -0.26
    èĭ¥å¹²
    -0.26
    ç¼ĸ
    -0.25
     bask
    -0.25
    ÑĥÑĩ
    -0.25
    æ°´å¹³
    -0.24
    -eng
    -0.24
    POSITIVE LOGITS
    onomic
    0.28
    ancy
    0.27
     cans
    0.25
    ÑİÑīим
    0.25
     vs
    0.25
    è¯įæĿ¡
    0.24
    ocom
    0.24
    幺
    0.24
    h
    0.23
    å°¹
    0.23
    Activations Density 3.165%

    No Known Activations