© 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. 63335
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions and articles

    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
    æĦĪ
    -0.27
    导
    -0.27
    vens
    -0.27
    WEEN
    -0.27
    agle
    -0.26
    @register
    -0.26
     mote
    -0.26
    çļĦéĤ£ä¸Ģ
    -0.26
    å°İ
    -0.25
     AppleWebKit
    -0.25
    POSITIVE LOGITS
    å½»
    0.26
     ext
    0.26
     unf
    0.25
    åĩĢåĢ¼
    0.25
    åģµ
    0.24
    被åĬ¨
    0.24
     unlock
    0.24
     beat
    0.23
    å¾¹
    0.23
     recip
    0.23
    Activations Density 28.616%

    No Known Activations