© 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. 130119
    Prev
    Next
    INDEX
    Explanations

    Scraped/Mixed data

    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
    çļĦèĦļæŃ¥
    -0.29
    -ajax
    -0.29
    tgt
    -0.28
    æĪijçĪ±ä½ł
    -0.27
    pecified
    -0.27
    ä¸ºæł¸å¿ĥçļĦ
    -0.26
    yleft
    -0.26
    为主é¢ĺçļĦ
    -0.25
    lient
    -0.25
    -aged
    -0.24
    POSITIVE LOGITS
    ä¸İæѤ
    0.32
    oload
    0.29
     mechanics
    0.26
    对æѤ
    0.26
    opes
    0.26
    客
    0.25
    åī²
    0.25
    为æѤ
    0.25
    ola
    0.23
    -delay
    0.23
    Activations Density 1.008%

    No Known Activations