© 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. 22-TRANSCODER-HP
    7. 88752
    Prev
    Next
    INDEX
    Explanations

    Single and/or English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    纵
    -0.27
    /*------------------------------------------------
    -0.27
    天
    -0.26
    çĨĬ
    -0.26
    许
    -0.25
    xffffff
    -0.25
    å¿ĥ
    -0.25
    èĤ¾
    -0.24
     ASS
    -0.24
    饱
    -0.24
    POSITIVE LOGITS
    "@
    0.30
    zee
    0.26
    产åĵģçļĦ
    0.25
    å·¥ä¸ļä¼ģä¸ļ
    0.25
    "^
    0.25
    oha
    0.25
    åºĶçĶ¨åľºæĻ¯
    0.24
    ç¼ĩ
    0.24
    )b
    0.24
    èĺħ
    0.24
    Activations Density 0.066%

    No Known Activations