© 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. 142634
    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
    ä¾ĭå¤ĸ
    -0.28
    å¸ĮæľĽéĢļè¿ĩ
    -0.27
    çĿģ
    -0.26
    æ¯ı次éĥ½
    -0.26
    edia
    -0.26
    å¸ĮæľĽ
    -0.26
    idia
    -0.26
    propri
    -0.26
    åĢŁ
    -0.26
     lender
    -0.25
    POSITIVE LOGITS
    èIJİ
    0.30
    ORS
    0.26
     vanish
    0.26
    mere
    0.26
    ors
    0.25
    å°Ķæĸ¯
    0.25
     indef
    0.25
     tamp
    0.25
    makt
    0.24
    蹶
    0.24
    Activations Density 18.113%

    No Known Activations

    This feature has no known activations.