© 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. 111072
    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
     revers
    -0.25
     twists
    -0.25
    åIJįåı«
    -0.25
     construct
    -0.25
    èįij
    -0.24
     effectively
    -0.24
     names
    -0.24
    éħĥ
    -0.24
     spins
    -0.24
     constructs
    -0.24
    POSITIVE LOGITS
    ä¸ĵ线
    0.29
    ä¾£
    0.28
    оÑĩнÑĭе
    0.26
    adox
    0.26
    æľī大éĩıçļĦ
    0.25
    éĿŀ常å¤ļ
    0.24
     окÑĢÑĥг
    0.24
    OL
    0.24
    DECLARE
    0.24
    سع
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.