© 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. 5008
    Prev
    Next
    INDEX
    Explanations

    Co-operative/communal structures

    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
    çļĦä¿¡ä»»
    -0.25
    ä¿¡ä»»
    -0.25
     favor
    -0.25
    vt
    -0.25
    uto
    -0.25
    atter
    -0.24
    arus
    -0.24
    çĮ¿
    -0.24
    .prepend
    -0.24
    æ²±
    -0.24
    POSITIVE LOGITS
    纤维
    0.28
     Fiber
    0.25
     bona
    0.24
    ë°©ìĨ¡
    0.24
    è´Ń
    0.24
     اÙĦÙĤرآÙĨ
    0.23
     ebook
    0.23
     jewel
    0.23
    è´Ń票
    0.23
     buying
    0.23
    Activations Density 0.018%

    No Known Activations