© 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. 5140
    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
    ÐļÑĥÑĢÑģ
    -0.28
    hd
    -0.27
     flattened
    -0.27
    æīģ
    -0.27
    äºĨä»ĸçļĦ
    -0.26
     UserDetails
    -0.24
    å¹³åĿ¦
    -0.24
    ="/">
    -0.23
     arriving
    -0.23
     getLocation
    -0.23
    POSITIVE LOGITS
    iders
    0.25
    æ¯ģ
    0.25
    impse
    0.24
    åĬ³åĬ¨åĬĽ
    0.24
    西éĥ¨
    0.24
    ainty
    0.24
    ionale
    0.24
    backs
    0.23
    ä¸ľè¥¿
    0.23
    _Impl
    0.23
    Activations Density 0.025%

    No Known Activations

    This feature has no known activations.