© 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. 38530
    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
    Negative Logits
    avian
    -0.28
    roup
    -0.28
    彤
    -0.27
    forge
    -0.26
    atorium
    -0.26
    lier
    -0.26
    èĬ¬
    -0.25
    æ¡¡
    -0.24
    ammen
    -0.24
    mor
    -0.24
    POSITIVE LOGITS
    å¾Ĵ
    0.29
     unl
    0.25
    çĸģ
    0.24
    åħ¶ä¸Ńä¸Ģ个
    0.24
     chrono
    0.24
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.24
     quotient
    0.24
    çİĵ
    0.24
    çĽijäºĭä¼ļ
    0.24
     mé
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.