© 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. 23-TRANSCODER-HP
    7. 25420
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æī
    -0.25
    annes
    -0.24
    udden
    -0.24
    çĬ¶
    -0.24
    å®ŀåľ¨
    -0.23
    æĬ¤å£«
    -0.23
    é¦ĸ个
    -0.23
    alled
    -0.23
    consistent
    -0.23
     unknown
    -0.23
    POSITIVE LOGITS
     promises
    0.29
    Fixture
    0.28
     dece
    0.26
    JR
    0.26
     hus
    0.26
    箸
    0.25
    俸
    0.25
    çݰ身
    0.24
    丢äºĨ
    0.24
    zeichnet
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.