© 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. 5116
    Prev
    Next
    INDEX
    Explanations

    Comparisons

    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
     presença
    -0.27
    碰
    -0.26
    触
    -0.26
    æĭįçħ§
    -0.24
    ä½İæĪIJæľ¬
    -0.24
    ÑĮе
    -0.24
    ä»ĺ款
    -0.24
     responsável
    -0.24
    è¯ļä¿¡
    -0.24
     strapped
    -0.23
    POSITIVE LOGITS
    tron
    0.27
    iness
    0.24
    ç°Ł
    0.24
    -inc
    0.24
    (em
    0.24
    elia
    0.24
    .dispose
    0.23
    weise
    0.23
    lico
    0.23
     hardest
    0.23
    Activations Density 0.020%

    No Known Activations