© 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. 62568
    Prev
    Next
    INDEX
    Explanations

    Question and answer snippets

    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
     alike
    -0.26
    çīĩ段
    -0.26
    egas
    -0.25
    Tuple
    -0.25
     glance
    -0.25
    anson
    -0.24
    }while
    -0.24
    labs
    -0.23
    chluss
    -0.23
    iciar
    -0.23
    POSITIVE LOGITS
    çļĦåĨħ容
    0.33
    jaw
    0.27
    æĭ©
    0.26
    content
    0.26
     content
    0.26
    åĨħ容
    0.26
    -content
    0.25
    æĪijçİ°åľ¨
    0.25
    æ¯ı次
    0.25
    设计çIJĨ念
    0.25
    Activations Density 30.915%

    No Known Activations