© 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. 161874
    Prev
    Next
    INDEX
    Explanations

    Instructions

    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
    票
    -0.32
    æĢ»ä»·
    -0.30
    äºĴéĢļ
    -0.26
    åĽłä¸ºä»ĸ们
    -0.26
     pushed
    -0.26
    åıĪèĥ½
    -0.25
    uran
    -0.25
    åIJ¸å¼ķæĽ´å¤ļ
    -0.24
     tickets
    -0.24
     trails
    -0.24
    POSITIVE LOGITS
    é¦ĸåħĪè¦ģ
    0.37
    é¦ĸåħĪ
    0.35
     firstly
    0.33
    第ä¸ĢæŃ¥
    0.32
     Firstly
    0.31
    ãģ¾ãģļ
    0.30
     먼ìłĢ
    0.29
    _Dep
    0.28
    ãģ¾ãģļãģ¯
    0.28
    ï¼Į请
    0.27
    Activations Density 0.003%

    No Known Activations