© 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. 64794
    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
    äºĶæľĪ
    -0.28
    åĨ·
    -0.25
     wÅĽ
    -0.24
     clicked
    -0.24
    æµģä¼ł
    -0.24
    ä¸ī代
    -0.23
    éĩįè§Ĩ
    -0.23
    æ±Ĺæ°´
    -0.23
    -Clause
    -0.23
    èŁł
    -0.23
    POSITIVE LOGITS
    cent
    0.27
    讽
    0.26
    å¾Ģ
    0.25
    ooter
    0.24
    èĥĦ
    0.24
    æµ·åı£
    0.24
    è¯ĥ
    0.24
    èĭ´
    0.23
     cent
    0.23
     certain
    0.23
    Activations Density 1.035%

    No Known Activations

    This feature has no known activations.