© 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. 6858
    Prev
    Next
    INDEX
    Explanations

    Technical questions/requests

    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
    createClass
    -0.28
    éĻĢ
    -0.28
    åıª
    -0.28
    èł²
    -0.27
    éĻIJå®ļ
    -0.27
    ä»ħ为
    -0.27
    ç®ĢåĮĸ
    -0.27
    ä½ķåĨµ
    -0.27
     subset
    -0.26
    _partial
    -0.26
    POSITIVE LOGITS
     instead
    0.47
    instead
    0.44
    æį¢æĪIJ
    0.40
     Instead
    0.39
    Instead
    0.38
     alternatively
    0.35
     ìķĦëĭĪëĿ¼
    0.34
    缸åıį
    0.34
    ãģ§ãģ¯ãģªãģı
    0.34
     rather
    0.33
    Activations Density 0.170%

    No Known Activations