© 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. 4813
    Prev
    Next
    INDEX
    Explanations

    Web content and code

    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
    æį®
    -0.37
     according
    -0.33
    æĵļ
    -0.31
     wedÅĤug
    -0.30
     ÑģоглаÑģ
    -0.30
    according
    -0.29
     REUTERS
    -0.27
     According
    -0.27
     bợi
    -0.26
     Guinness
    -0.25
    POSITIVE LOGITS
    çł´
    0.35
    æīĵçł´
    0.28
    wh
    0.28
     breaking
    0.28
    èŀį
    0.27
    iter
    0.26
    asters
    0.26
     wh
    0.26
    ç´
    0.26
    第ä¸ĢæĿ¡
    0.26
    Activations Density 0.153%

    No Known Activations