© 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. 38710
    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
    oire
    -0.26
    éparation
    -0.26
     goal
    -0.22
    ãģIJãĤīãģĦ
    -0.22
    éĶ·
    -0.22
    reation
    -0.22
    æķ´åIJĪ
    -0.22
     introductory
    -0.22
     ratio
    -0.22
     flagship
    -0.22
    POSITIVE LOGITS
    å²Ķ
    0.26
    çģ¾éļ¾
    0.25
    身ä½ĵåģ¥åº·
    0.25
    á»Ńa
    0.25
    çģ¾
    0.24
    æĺ¼å¤ľ
    0.24
    温
    0.24
    软
    0.24
    åħ´å¥ĭ
    0.23
    紧迫
    0.23
    Activations Density 2.821%

    No Known Activations

    This feature has no known activations.