© 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. 21947
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    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
    .sharedInstance
    -0.29
     benchmarks
    -0.28
    é²Ī
    -0.26
    universal
    -0.25
     universal
    -0.24
     swapped
    -0.24
    请æĤ¨
    -0.24
    lashes
    -0.24
    éĢļçĶ¨
    -0.24
    _LP
    -0.23
    POSITIVE LOGITS
     Explain
    0.29
    å¢ŀè¿Ľ
    0.29
     speeding
    0.27
    å±ķè§Īä¼ļ
    0.27
     speed
    0.27
    ä¸ĢéĿ¢
    0.27
    -speed
    0.27
     Expl
    0.25
     explain
    0.25
    ìŀĶ
    0.25
    Activations Density 0.001%

    No Known Activations