© 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. 22-TRANSCODER-HP
    7. 128894
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     readline
    -0.25
    å®Ŀ
    -0.24
    á»Ĩ
    -0.23
    ç«¿
    -0.23
     å½ĵ
    -0.22
    ä¼ĺè´¨
    -0.22
    åĪ©å¥½
    -0.22
    ably
    -0.22
    wait
    -0.21
    以åıĬåħ¶ä»ĸ
    -0.21
    POSITIVE LOGITS
    æ³Ĭ
    0.28
    bedo
    0.24
    ystems
    0.24
    羣åĪĩ
    0.23
     AttributeSet
    0.23
    裸
    0.23
     citas
    0.23
     Decorating
    0.23
     Opening
    0.22
     plage
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.