© 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. 241
    Prev
    Next
    INDEX
    Explanations

    software code

    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
    åºĬä¸Ĭ
    -0.28
    hausen
    -0.28
    iem
    -0.27
    æĪĸå¤ļ
    -0.27
    itor
    -0.27
    责任ç¼ĸè¾ij
    -0.25
    èįĨå·ŀ
    -0.24
    çĸ³
    -0.24
    好å¥ĩå¿ĥ
    -0.24
    tle
    -0.24
    POSITIVE LOGITS
     Mov
    0.25
     movement
    0.24
     movements
    0.24
    éĤ£ä»½
    0.24
    ä¸ĸ
    0.24
     aval
    0.24
    æĹĮ
    0.23
    ży
    0.23
     motion
    0.23
    -inc
    0.22
    Activations Density 0.090%

    No Known Activations