© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5072
    Prev
    Next
    INDEX
    Explanations

    colons

    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
    æľĪ以æĿ¥
    -0.29
    人éĹ´
    -0.27
    æĹ¥
    -0.27
    Swift
    -0.27
    ed
    -0.26
    çŃīçĿĢ
    -0.26
    è¿Ļå°±æĺ¯
    -0.26
    è¿Ļå°±
    -0.26
    æĹ¥èĩ³
    -0.26
    .Com
    -0.26
    POSITIVE LOGITS
    veled
    0.27
    /Delete
    0.26
     adam
    0.26
     occasionally
    0.25
    ocop
    0.25
    andin
    0.25
    DMI
    0.24
    oup
    0.24
    ancode
    0.23
    (Initialized
    0.23
    Activations Density 0.034%

    No Known Activations