© 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. 6037
    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
    åŃIJå¼Ł
    -0.29
    aining
    -0.27
     foot
    -0.25
    /free
    -0.24
    INF
    -0.24
    ä»İå°ı
    -0.24
    åĺı
    -0.24
    izzo
    -0.23
    ì¤ij
    -0.23
     gravy
    -0.23
    POSITIVE LOGITS
    èĤī
    0.30
     Tune
    0.27
     MSR
    0.26
    moth
    0.26
    æĬĹè®®
    0.25
    ivr
    0.25
    çļĦç¨ĭ度
    0.24
    ivent
    0.24
    æĸ¹å¼ıè¿Ľè¡Į
    0.23
    åİ»çľĭ
    0.23
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.