© 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. 35-TRANSCODER-HP
    7. 40463
    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
    æīİ
    -0.27
     contr
    -0.27
     theory
    -0.26
    ãģ¾ãģ¾
    -0.25
     results
    -0.25
    å°ıåŀĭ
    -0.25
     Option
    -0.25
     Ãĸ
    -0.24
    åİŁåĽł
    -0.24
     fact
    -0.24
    POSITIVE LOGITS
    fills
    0.26
    欢è¿İæĤ¨
    0.26
    ä»ĸæĺ¯ä¸Ģ个
    0.26
     symbolic
    0.26
    æĪijçĪ±ä½ł
    0.25
    符åı·
    0.25
     identifies
    0.25
     communicates
    0.25
    èĥ½æĬĬ
    0.25
    è¡Į使
    0.25
    Activations Density 5.250%

    No Known Activations

    This feature has no known activations.