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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7187
    Prev
    Next
    INDEX
    Explanations

    Questions, answers, lists

    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
    è¿Ľé©»
    -0.26
     IRepository
    -0.26
    iad
    -0.26
     fathers
    -0.26
     consciously
    -0.25
     лÑİ
    -0.24
    åīįç½®
    -0.24
    æľīéĹ®é¢ĺ
    -0.23
     advert
    -0.23
    ERS
    -0.23
    POSITIVE LOGITS
    stance
    0.26
    å¼¹æĢ§
    0.25
    檬
    0.25
    imals
    0.24
    VAR
    0.24
    éĽĢ
    0.24
    asy
    0.23
    iska
    0.23
    ↵↵↵↵↵
    0.23
    å·©åĽº
    0.23
    Activations Density 0.024%

    No Known Activations