© 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. 230
    Prev
    Next
    INDEX
    Explanations

    ude

    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
    BUS
    -0.28
    ä½Ĩè¿Ļ
    -0.26
    象
    -0.26
    ÑģÑĤе
    -0.25
    é¢ľåĢ¼
    -0.24
    æĥ³è±¡
    -0.24
    çļĦè·¯ä¸Ĭ
    -0.24
    loff
    -0.24
    .central
    -0.23
    anas
    -0.23
    POSITIVE LOGITS
    .shtml
    0.30
     Rewrite
    0.28
     ########.
    0.26
    ź
    0.25
     Uncomment
    0.25
    第ä¸īèĢħ
    0.24
    opensource
    0.24
     ipt
    0.24
     owed
    0.24
     trustees
    0.24
    Activations Density 0.019%

    No Known Activations