© 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. 129011
    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
     probable
    -0.24
    âĢĸ
    -0.24
    继ç»Ń
    -0.24
     воÑĤ
    -0.24
     floor
    -0.24
    éĢļæĬ¥
    -0.24
    EMPL
    -0.23
    ç»´å¥ĩ
    -0.23
    对çħ§
    -0.23
    æħ°
    -0.23
    POSITIVE LOGITS
    TableRow
    0.27
    å¸Ĥå§Ķ常å§Ķ
    0.25
    udden
    0.25
    acci
    0.24
    æīĵçł´äºĨ
    0.23
    olders
    0.23
    tables
    0.23
    ÃŃsimo
    0.23
    DataRow
    0.23
    mighty
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.