© 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. 5159
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ountry
    -0.28
    arris
    -0.28
    ä¸Ģ次æĢ§
    -0.24
    æįķ
    -0.24
    _substr
    -0.24
     agent
    -0.24
    bro
    -0.24
    æľºåħ³
    -0.24
     optionally
    -0.23
    主è§Ĥ
    -0.23
    POSITIVE LOGITS
    ignKey
    0.32
    astery
    0.28
    лей
    0.25
    adas
    0.24
    ados
    0.24
    adies
    0.24
    amedi
    0.23
    ä¸įä¸ĭ
    0.23
    eten
    0.23
    第ä¸Ģ书记
    0.23
    Activations Density 0.718%

    No Known Activations

    This feature has no known activations.