© 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. 62839
    Prev
    Next
    INDEX
    Explanations

    Web content or code

    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
    让åѦçĶŁ
    -0.28
    bildung
    -0.26
    bang
    -0.25
     пÑĢедназ
    -0.25
     minor
    -0.25
     Minor
    -0.25
    å°ijéĩı
    -0.25
     proper
    -0.25
    åı¯ä»¥è®©
    -0.25
     pred
    -0.25
    POSITIVE LOGITS
    RuleContext
    0.27
     incest
    0.26
    é«ĺç´łè´¨
    0.26
    尽头
    0.25
    INCLUDED
    0.25
    LoggedIn
    0.25
    ç»ĪçĤ¹
    0.25
    باÙĨ
    0.25
    ):-
    0.25
     PAC
    0.24
    Activations Density 1.704%

    No Known Activations