© 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. 19-TRANSCODER-HP
    7. 9424
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è°¨
    -0.32
    管çIJĨå±Ģ
    -0.30
    åı·çłģ
    -0.28
    dings
    -0.28
    мÑĭÑĪ
    -0.27
    ObjectName
    -0.25
    åľ¨åħ¶
    -0.25
    æĢĿ
    -0.25
     semi
    -0.25
    uel
    -0.25
    POSITIVE LOGITS
     palate
    0.33
    aign
    0.28
     Cf
    0.26
     Oval
    0.25
     Coach
    0.25
    }}},↵
    0.24
    ä¸Ģäºĭ
    0.24
    adh
    0.24
    enance
    0.24
    壮
    0.24
    Activations Density 0.052%

    No Known Activations

    This feature has no known activations.