© 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. 129906
    Prev
    Next
    INDEX
    Explanations

    Mixed writing styles/sources

    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
     powered
    -0.29
     Powered
    -0.27
    åģļ好
    -0.27
    ijľ
    -0.26
     last
    -0.26
    å¹´å¼Ģå§ĭ
    -0.26
     than
    -0.26
     chained
    -0.25
     Suffolk
    -0.25
    åħ³äºİ
    -0.25
    POSITIVE LOGITS
    [dir
    0.29
     ResourceManager
    0.28
    =in
    0.27
    çĶ»éĿ¢
    0.25
    UIApplication
    0.25
     PMC
    0.25
    scenes
    0.25
     heiÃŁ
    0.24
    coc
    0.24
    -dir
    0.24
    Activations Density 0.570%

    No Known Activations