© 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. 88120
    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
    å¢ĥåĨħ
    -0.30
     centered
    -0.28
    èIJ¥
    -0.27
     Contacts
    -0.26
    å°Ĩ以
    -0.25
    ryptography
    -0.25
    æį
    -0.24
     towards
    -0.24
    -cent
    -0.24
    agrams
    -0.24
    POSITIVE LOGITS
    uge
    0.28
    UpDown
    0.28
    åģļåĩº
    0.28
    涨
    0.27
     Suit
    0.26
    Suit
    0.25
    æݧåĪ¶ç³»ç»Ł
    0.25
    +i
    0.24
    ç¬ŀ
    0.24
    anager
    0.24
    Activations Density 3.667%

    No Known Activations

    This feature has no known activations.