© 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. 4-TRANSCODER-HP
    7. 119
    Prev
    Next
    INDEX
    Explanations

    implementation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anity
    -0.27
    éĢĶ
    -0.25
    idel
    -0.25
    olib
    -0.24
    andom
    -0.24
    :\/\/
    -0.23
    åIJĮæľŁ
    -0.23
    ANDOM
    -0.23
    æĹłåı¯
    -0.23
    æľī两个
    -0.23
    POSITIVE LOGITS
    è¾¹ä¸Ĭ
    0.28
    åĶ¤
    0.27
    (~
    0.27
     distância
    0.26
    warts
    0.26
    ä¹ĭä¸ĭ
    0.25
    年纪
    0.25
    (||
    0.25
    arde
    0.25
    åĪĨæ³Į
    0.24
    Activations Density 0.038%

    No Known Activations