© 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. 23987
    Prev
    Next
    INDEX
    Explanations

    meat, 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
    ationally
    -0.27
    _blocking
    -0.27
    frame
    -0.26
    еÑĩен
    -0.26
    active
    -0.25
     ëªħ
    -0.25
    åIJijåīį
    -0.24
    um
    -0.24
    ioctl
    -0.24
     zwiÄħz
    -0.24
    POSITIVE LOGITS
    ä¸Ńå¿ĥ主任
    0.27
    æľ¬æĬ¥è®¯
    0.26
    REFER
    0.26
     Astroph
    0.26
     bindActionCreators
    0.26
     kil
    0.26
     Astr
    0.25
     kits
    0.25
     Danger
    0.25
    asting
    0.24
    Activations Density 0.000%

    No Known Activations