© 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. 19-TRANSCODER-HP
    7. 9391
    Prev
    Next
    INDEX
    Explanations

    News/Promotional content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼ķåħ¥
    -0.26
    ableObject
    -0.25
    ifecycle
    -0.25
    	elem
    -0.24
    oreach
    -0.24
    åħĥ件
    -0.24
     Except
    -0.24
    isory
    -0.23
     Covered
    -0.23
    plier
    -0.23
    POSITIVE LOGITS
    辫
    0.29
     kans
    0.28
     shadow
    0.28
    shadow
    0.27
     late
    0.27
    itä
    0.26
    ede
    0.26
    ãģıãģł
    0.25
    ä¸Ģ个æľĪ
    0.24
     bootstrap
    0.24
    Activations Density 0.299%

    No Known Activations