© 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
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 6099
    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
    ãģĻãģİ
    -0.28
    ainer
    -0.27
    enance
    -0.27
    ainment
    -0.26
    èle
    -0.26
     Station
    -0.25
     legitim
    -0.25
    apon
    -0.24
    ä¼ļåIJĮ
    -0.24
    çīĮçħ§
    -0.23
    POSITIVE LOGITS
    女ç¥ŀ
    0.26
    éĹ»
    0.25
     Valentine
    0.24
    )[:
    0.24
    ç§ijå¹»
    0.24
    LOAD
    0.24
    flow
    0.24
     deduct
    0.24
    å¯ĴåĨ·
    0.23
    Ĥ¬
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.