© 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. 30-TRANSCODER-HP
    7. 95001
    Prev
    Next
    INDEX
    Explanations

    should

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     dipping
    -0.32
     lap
    -0.28
     checked
    -0.27
     input
    -0.27
     check
    -0.27
     checking
    -0.26
     introdu
    -0.25
    input
    -0.25
    lee
    -0.24
    åıĪ被
    -0.24
    POSITIVE LOGITS
    åħ¬
    0.26
    ç½ijå°ıç¼ĸ
    0.26
    krit
    0.25
    ä¸įèĩ³äºİ
    0.25
     Publi
    0.25
    _EXTERN
    0.25
    笼
    0.24
    bands
    0.24
    æĪijæīį
    0.24
    endra
    0.23
    Activations Density 0.004%

    No Known Activations