© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40197
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺ¯ä¸Ģ件
    -0.28
    èĢĮåİ»
    -0.27
    ainers
    -0.27
    åİ»äºĨ
    -0.24
     Herc
    -0.24
    atas
    -0.23
    itori
    -0.23
     DataAccess
    -0.23
    å¤©åľ°
    -0.23
     userDetails
    -0.23
    POSITIVE LOGITS
    kn
    0.25
    æłĵ
    0.25
    strand
    0.25
    驼
    0.24
    (sim
    0.24
     embargo
    0.23
     dad
    0.23
     dem
    0.23
    æĿ¡ä»¶ä¸ĭ
    0.23
    çŃīæĸ¹å¼ı
    0.22
    Activations Density 26.448%

    No Known Activations

    This feature has no known activations.