© 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. 24246
    Prev
    Next
    INDEX
    Explanations

    lion

    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
     milan
    -0.25
    å¾µ
    -0.25
    ü
    -0.24
     borrowing
    -0.24
    éģ£
    -0.24
    åĢŁçĶ¨
    -0.23
    çĭ¬èĩª
    -0.23
    åѤçĭ¬
    -0.23
     viewType
    -0.23
    DOCUMENT
    -0.23
    POSITIVE LOGITS
    鼷éľĨ
    0.26
    人大
    0.26
     hotspot
    0.26
    ruta
    0.25
     heck
    0.25
    çĥŃçĤ¹
    0.24
    奶èĮ¶
    0.24
    paration
    0.24
    strate
    0.24
    说è¿ĩ
    0.24
    Activations Density 0.029%

    No Known Activations