© 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. 4933
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ega
    -0.28
    umpt
    -0.26
     Andrews
    -0.26
    æĿ¥çĶµ
    -0.26
    icide
    -0.25
    abinet
    -0.25
    hic
    -0.25
    ste
    -0.25
    andin
    -0.24
    æĬĢæľ¯çłĶåıij
    -0.24
    POSITIVE LOGITS
    isify
    0.26
     pans
    0.25
    æľīä¸Ģ
    0.24
    èİ·è¯Ħ
    0.23
     ÙĦدÙĬ
    0.23
    lijk
    0.23
    åĿļæĮģ以
    0.23
    æľīå¤ļå°ij
    0.23
    IMP
    0.23
    楹
    0.23
    Activations Density 0.354%

    No Known Activations