© 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. 38701
    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
    年级
    -0.29
    åĽłèĢĮ
    -0.28
    èĪŀåı°
    -0.27
    æĽ´å¤ļ
    -0.27
    æį¢
    -0.27
    æŃ£ç¡®
    -0.26
    çݯèĬĤ
    -0.26
    èĮĥçķ´
    -0.26
    æĽ´å¥½
    -0.25
    åħ¶å®ĥ
    -0.25
    POSITIVE LOGITS
    ëħ¹
    0.28
    娩
    0.27
    íİĢ
    0.26
    @mail
    0.26
    åīįä¸ĸ
    0.25
    Ñĩик
    0.24
     Lowe
    0.24
    çĹ«
    0.24
    缸çĪ±
    0.23
     interrupted
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.