© 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. 20-TRANSCODER-HP
    7. 64666
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æī«ä¸Ģæī«
    -0.29
    intern
    -0.28
     Lynch
    -0.25
    dra
    -0.25
     Dra
    -0.25
    \Seeder
    -0.24
    rolley
    -0.24
    å°±èĥ½
    -0.24
    rowsing
    -0.23
    éĿŀ常好
    -0.23
    POSITIVE LOGITS
     Pru
    0.28
    ä¸į该
    0.28
    çĮľæµĭ
    0.27
    æĭ¬
    0.26
    åħľ
    0.26
    uko
    0.25
    ç¡Ģ
    0.25
    è´§å¸ģ
    0.24
    ques
    0.24
     Colomb
    0.24
    Activations Density 5.856%

    No Known Activations

    This feature has no known activations.