© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161980
    Prev
    Next
    INDEX
    Explanations

    every/each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bou
    -0.28
    æĺİæĺİ
    -0.27
    ä¸¤å¼ł
    -0.27
     atan
    -0.27
    otti
    -0.26
     opted
    -0.26
    Broken
    -0.25
    Ñĩки
    -0.25
     EXPRESS
    -0.25
    两次
    -0.24
    POSITIVE LOGITS
    æ¯ıå¹´
    0.30
    umber
    0.27
     года
    0.27
    年度
    0.27
     running
    0.26
    ç¼Ģ
    0.26
    æ¯ıå¹´éĥ½
    0.25
     year
    0.25
    acle
    0.24
    ager
    0.24
    Activations Density 0.005%

    No Known Activations