© 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. 21927
    Prev
    Next
    INDEX
    Explanations

    music

    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
    ä½ľçĶ¨
    -0.31
     Acting
    -0.29
    åħ¬å®ī
    -0.28
    èŃ¦å¯Ł
    -0.27
    Ļ¶
    -0.26
    ä¼ĺåħĪ
    -0.25
    ä¼łè¾¾
    -0.25
    代表çĿĢ
    -0.24
    äºĨå¤ļå°ij
    -0.24
    å¸Ĥåħ¬å®īå±Ģ
    -0.24
    POSITIVE LOGITS
    欣
    0.27
    æĸ°ä¸ī
    0.27
    ARTH
    0.27
    ÂŃi
    0.27
    oldt
    0.26
     flatt
    0.26
    elas
    0.26
     Walton
    0.25
    uki
    0.25
    iesel
    0.25
    Activations Density 0.000%

    No Known Activations