© 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. 30-TRANSCODER-HP
    7. 97152
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     kü
    -0.30
     fres
    -0.27
     BET
    -0.25
    飧
    -0.25
    éĢĴ
    -0.24
    sea
    -0.24
     fatalError
    -0.24
     cash
    -0.24
     Fres
    -0.24
    ms
    -0.24
    POSITIVE LOGITS
    ucha
    0.29
     thẩm
    0.28
    æĶ¯æŀ¶
    0.26
    ÑĢак
    0.25
    ä¸įèĪį
    0.25
    ained
    0.25
     Obt
    0.24
    ibus
    0.24
     Frames
    0.24
    (frames
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.