© 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. 140985
    Prev
    Next
    INDEX
    Explanations

    D

    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
    æĮij
    -0.28
    éŀł
    -0.25
     punched
    -0.24
    æ¸ħæ°´
    -0.24
    满æĦıçļĦ
    -0.23
    صÙĬب
    -0.23
    åĤħ
    -0.23
     bubb
    -0.23
     bios
    -0.23
    ä¸įçŁ¥éģĵ
    -0.23
    POSITIVE LOGITS
    0.32
    oard
    0.28
    åĪ°æĿ¥
    0.27
    onclick
    0.26
    æĶ¶å½ķ
    0.25
     Major
    0.25
    á»ijn
    0.24
    á¹ħ
    0.24
     #č↵
    0.24
    鹧
    0.24
    Activations Density 51.868%

    No Known Activations