© 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. 142526
    Prev
    Next
    INDEX
    Explanations

    ocom

    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
    Resolved
    -0.26
    åĮĹæĸ¹
    -0.26
    ifest
    -0.26
    jr
    -0.26
     fran
    -0.26
    uala
    -0.25
     Yankee
    -0.25
    å¼Ħ
    -0.25
    jmp
    -0.24
    åħŃåįģ
    -0.24
    POSITIVE LOGITS
    LETTE
    0.26
    çļĦèģĮä¸ļ
    0.26
    åĴĮ社ä¼ļ
    0.25
    æŃĨ
    0.25
    iator
    0.24
    IJľ
    0.24
    atial
    0.24
    ién
    0.24
    交è°Ī
    0.24
    олÑĮз
    0.23
    Activations Density 4.621%

    No Known Activations