© 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. 24001
    Prev
    Next
    INDEX
    Explanations

    further

    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
    AndView
    -0.29
    tempt
    -0.28
    ä»£æĽ¿
    -0.27
    orate
    -0.27
    åģļ强
    -0.26
    è°ģçŁ¥éģĵ
    -0.26
    éªĭ
    -0.26
    erset
    -0.26
    åį´åıijçİ°
    -0.26
    产åĵģè´¨éĩı
    -0.26
    POSITIVE LOGITS
    cÃŃ
    0.29
    çļĦå°±æĺ¯
    0.28
    ennon
    0.27
    ä¸Ģå¤Ħ
    0.27
     yazılı
    0.25
     paid
    0.25
    jax
    0.25
    è°¦
    0.24
    J
    0.24
    æ½ĺ
    0.24
    Activations Density 0.014%

    No Known Activations