© 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. 6276
    Prev
    Next
    INDEX
    Explanations

    technical/systems support

    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
     -:
    -0.29
    夹
    -0.26
    ighted
    -0.25
    æľŁåĨħ
    -0.25
    åIJIJ槽
    -0.24
    å²ģæŶ
    -0.24
     vintage
    -0.24
    ä»įçĦ¶æĺ¯
    -0.24
     kali
    -0.24
    å¹´ãģ®
    -0.23
    POSITIVE LOGITS
     Split
    0.28
    scious
    0.26
    èĢĥåľº
    0.26
     Hispan
    0.26
    çļĦä¸įåIJĮ
    0.25
     lo
    0.25
    (split
    0.25
    åIJİæİĴ
    0.25
    etten
    0.25
    \č↵
    0.24
    Activations Density 0.013%

    No Known Activations