© 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. 22017
    Prev
    Next
    INDEX
    Explanations

    electrolytes and medical conditions

    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
    imest
    -0.28
     OSS
    -0.27
     open
    -0.26
    Open
    -0.26
    车çīĮ
    -0.25
    å¼ĢæĶ¾
    -0.25
    p
    -0.25
    abeled
    -0.24
    ä½ĵåĪ¶
    -0.24
    aturas
    -0.24
    POSITIVE LOGITS
     Tyson
    0.27
     meaning
    0.26
    æı¡ä½ı
    0.26
    æľºæ¢°è®¾å¤ĩ
    0.25
    moid
    0.25
     zona
    0.24
     THANK
    0.24
    èįı
    0.24
    //---------------------------------------------------------------------------↵↵
    0.24
    è§ļ
    0.23
    Activations Density 0.003%

    No Known Activations