© 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. 21997
    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
    (script
    -0.28
    iben
    -0.26
    ÊĻ
    -0.24
    unan
    -0.24
    agg
    -0.24
    溧
    -0.24
    еÑĩен
    -0.24
    aptive
    -0.24
     script
    -0.24
    inkle
    -0.24
    POSITIVE LOGITS
    jeta
    0.28
     enlargement
    0.26
    ORIGINAL
    0.26
     Chúa
    0.26
     назад
    0.24
    ãĤ¹ãĥ¼ãĥij
    0.24
    宽
    0.24
    _beh
    0.24
    çĬ¯è§Ħ
    0.23
    èįª
    0.23
    Activations Density 0.000%

    No Known Activations