© 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. 18-TRANSCODER-HP
    7. 90037
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ove
    -0.27
    æįŁ
    -0.27
    æ´Ĺå¹²åĩĢ
    -0.27
    Ñĩин
    -0.25
    交æį¢
    -0.25
    åŃIJéĩĮ
    -0.25
    çĭ¬ä¸ĢæĹłäºĮ
    -0.25
    iveness
    -0.24
    @class
    -0.24
    ä¸ĬéĿ¢
    -0.24
    POSITIVE LOGITS
     Clar
    0.29
    主æĦı
    0.29
     Locker
    0.26
     Albany
    0.26
     Ans
    0.26
    -au
    0.26
     Warner
    0.25
     Corn
    0.25
     robotic
    0.25
    åłĨ积
    0.25
    Activations Density 81.189%

    No Known Activations

    This feature has no known activations.