© 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. 12-TRANSCODER-HP
    7. 22056
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Pais
    -0.27
    edly
    -0.27
    éĢģåĩº
    -0.26
    LAT
    -0.26
    èĥ½å¤Łè®©
    -0.25
    Äįe
    -0.24
     sampled
    -0.24
    uest
    -0.24
    ç´§
    -0.24
    èģĨ
    -0.24
    POSITIVE LOGITS
    请大家
    0.29
    pin
    0.26
    sville
    0.25
     consid
    0.25
    èĶĵ
    0.24
    èĢĥ
    0.24
    -ajax
    0.24
    eline
    0.24
     Conor
    0.24
     object
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.