© 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. 90201
    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
    Negative Logits
     kings
    -0.28
    çļĦ大
    -0.28
    osit
    -0.27
    å¿¡
    -0.27
    opsis
    -0.26
    åı¶
    -0.25
     Kings
    -0.25
    éŃĶçİĭ
    -0.24
    çļĦåĬ¨ä½ľ
    -0.23
    иÑĢовки
    -0.23
    POSITIVE LOGITS
    uhl
    0.34
    lez
    0.31
    AMY
    0.28
    æĶ¶æķĽ
    0.28
    먼
    0.27
    ĽĦ
    0.27
    Ŀå§ĭ
    0.25
    俱ä¹IJéĥ¨
    0.25
    æľįåĬ¡å¹³åı°
    0.25
     jumper
    0.24
    Activations Density 2.913%

    No Known Activations

    This feature has no known activations.