© 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. 5081
    Prev
    Next
    INDEX
    Explanations

    Random text 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
    åĨł
    -0.26
     thief
    -0.25
    arter
    -0.25
    uzzle
    -0.25
     :↵↵↵↵
    -0.24
    locker
    -0.24
    erald
    -0.24
     bindActionCreators
    -0.24
    stra
    -0.23
     empir
    -0.23
    POSITIVE LOGITS
    odos
    0.28
    åĨĪ
    0.26
    physical
    0.26
    [to
    0.26
    第ä¸Ģ个
    0.25
    kur
    0.24
    çī©çIJĨ
    0.24
    éķ¿å¤§
    0.24
    opened
    0.24
    -awesome
    0.24
    Activations Density 0.001%

    No Known Activations