© 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. 21966
    Prev
    Next
    INDEX
    Explanations

    filenames and uppercase names

    np_max-act · gemini-2.0-flash
    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
    å¼¹
    -0.31
     kicker
    -0.30
    å¼
    -0.29
    ;element
    -0.28
     firing
    -0.26
    éĺĹ
    -0.25
    鸡èĽĭ
    -0.25
    åºĶèģĺ
    -0.24
    bearing
    -0.24
    æĬijéĥģ
    -0.24
    POSITIVE LOGITS
    iom
    0.26
    éĿ¢
    0.25
    iores
    0.25
    è¶ħé«ĺ
    0.25
    .super
    0.24
     harness
    0.24
    AIL
    0.24
    ноÑģÑĤÑĮÑİ
    0.24
    ior
    0.24
     (-
    0.24
    Activations Density 0.001%

    No Known Activations