© 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. 24258
    Prev
    Next
    INDEX
    Explanations

    Code and non-natural language

    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
    æѤ类
    -0.29
    ieves
    -0.27
     alike
    -0.26
    -breaking
    -0.25
    èĢĮéĿŀ
    -0.24
    rather
    -0.24
    ç½ijåıĭè¯Ħ论
    -0.24
    PL
    -0.24
    pras
    -0.24
     rather
    -0.24
    POSITIVE LOGITS
    å¢Ļ
    0.35
    çīĨ
    0.31
    å¢Ļä¸Ĭ
    0.30
    å¢Ļå£ģ
    0.27
    onda
    0.27
    å¢Ļä½ĵ
    0.27
    é©·
    0.27
    建çŃijæĿIJæĸĻ
    0.26
    åıij表äºĨ
    0.25
    棺
    0.25
    Activations Density 0.001%

    No Known Activations