© 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. 162930
    Prev
    Next
    INDEX
    Explanations

    movement

    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
    åľ¨ä¸Ģ个
    -0.35
    ç»Ļ人
    -0.28
    åľ¨æĹ¥æľ¬
    -0.27
    åľ¨åĽ½å¤ĸ
    -0.27
    åıij表
    -0.26
    åľ¨æľªæĿ¥
    -0.26
    åľ¨
    -0.26
    åľ¨åIJĮä¸Ģ
    -0.26
     contacting
    -0.26
    ä¸Ĭåİ»
    -0.26
    POSITIVE LOGITS
    åĨ¥
    0.30
    æ·ĩ
    0.28
     scene
    0.27
     wind
    0.27
     over
    0.27
    /arch
    0.26
    ä¸įäºĨ
    0.26
    èŀįåĮĸ
    0.25
    hil
    0.25
    ducted
    0.24
    Activations Density 0.017%

    No Known Activations