© 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. 25346
    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
    avage
    -0.27
    á»ģn
    -0.25
    quiries
    -0.25
    otonin
    -0.24
    cro
    -0.24
     queryInterface
    -0.24
    actics
    -0.23
    ager
    -0.23
     darker
    -0.23
    ={['
    -0.23
    POSITIVE LOGITS
    åĬ²
    0.28
    éĿ¢åŃIJ
    0.27
    URRENCY
    0.26
    ä¸İåħ¶
    0.25
    éĩįç£ħ
    0.25
    åĭģ
    0.25
    æł·çļĦ
    0.24
    åıĪ好åıĪ
    0.24
    çļĦè¯Ńè¨Ģ
    0.24
    é¼ĵ
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.