© 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. 19-TRANSCODER-HP
    7. 4980
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åģ»
    -0.28
    çݰ代åĨľä¸ļ
    -0.27
     deco
    -0.26
    认åı¯
    -0.26
    èĦ±é¢ĸ
    -0.25
    åĴĮ社ä¼ļ
    -0.24
    _Master
    -0.24
    ÑĢин
    -0.23
    RI
    -0.23
    社ä¼ļåĮĸ
    -0.23
    POSITIVE LOGITS
    éĻĤ
    0.27
    顽强
    0.24
     Ñģебе
    0.24
    è±ķ
    0.23
     boarded
    0.23
    -posts
    0.23
     Begins
    0.23
    Coroutine
    0.23
    eing
    0.23
    移æ¤į
    0.23
    Activations Density 0.007%

    No Known Activations