© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6794
    Prev
    Next
    INDEX
    Explanations

    ivity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įåĪ©
    -0.28
     chrom
    -0.28
    .CR
    -0.26
    æľīæĿ¡ä»¶
    -0.26
     carefully
    -0.25
    velop
    -0.25
     Chromium
    -0.25
    ç¦ģå¿Į
    -0.24
    (ht
    -0.24
    æīĵåħ¥
    -0.24
    POSITIVE LOGITS
    æĹłéľĢ
    0.27
    ãģ®æĸ¹ãģĮ
    0.26
    群
    0.25
    èĢĮå·²
    0.25
    羣
    0.25
    形容
    0.25
    å·²äºİ
    0.24
    ricks
    0.24
    å¡ŀ
    0.24
     almost
    0.24
    Activations Density 0.013%

    No Known Activations