© 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. 108494
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çIJĨ解åĴĮ
    -0.26
    èıľèĤ´
    -0.25
    解æŀIJ
    -0.25
    nels
    -0.25
    >Edit
    -0.25
    еÑĢÑĤ
    -0.24
    å¹³åı°ä¸Ĭ
    -0.24
    çģµ
    -0.24
     Moff
    -0.23
    STD
    -0.23
    POSITIVE LOGITS
    ude
    0.26
    udi
    0.26
     deadly
    0.26
    aldi
    0.25
     survival
    0.25
    ETH
    0.24
    iola
    0.24
     survive
    0.24
    ½æķ°
    0.24
    	speed
    0.23
    Activations Density 0.324%

    No Known Activations