© 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. 20-TRANSCODER-HP
    7. 64641
    Prev
    Next
    INDEX
    Explanations

    technical/scientific documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ÑĩÑĮ
    -0.31
    ckeditor
    -0.28
    ersed
    -0.28
    ếp
    -0.28
    AWS
    -0.25
    第ä¸ĢæĿ¡
    -0.25
    _bp
    -0.25
    азв
    -0.24
    NoSuch
    -0.24
    аниÑİ
    -0.24
    POSITIVE LOGITS
    pair
    0.27
    (Self
    0.26
     proudly
    0.26
    åĽ½ç±į
    0.25
     ref
    0.25
    å¹³åı°ä¸Ĭ
    0.24
     pair
    0.24
    (fragment
    0.24
    ndl
    0.24
     sam
    0.23
    Activations Density 1.699%

    No Known Activations