© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130319
    Prev
    Next
    INDEX
    Explanations

    updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sizer
    -0.28
    imizer
    -0.26
    åľ»
    -0.26
    oug
    -0.26
     jugg
    -0.25
    ystore
    -0.25
    åĽłä¸ºä»ĸ们
    -0.25
     specials
    -0.24
    otas
    -0.24
    atura
    -0.24
    POSITIVE LOGITS
    åıij
    0.28
    åģ¶
    0.27
    utta
    0.26
    äºĪ以
    0.26
     deriv
    0.25
    æ²»
    0.25
    derived
    0.25
    åĬŀåħ¬å®¤
    0.24
     consistently
    0.24
    ä¹łè¿ijå¹³
    0.24
    Activations Density 2.728%

    No Known Activations