© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9163
    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
    åIJ¹
    -0.33
    è´¯éĢļ
    -0.25
     berth
    -0.24
    æŃ¥è¡Į
    -0.24
    cta
    -0.24
    @brief
    -0.24
    edata
    -0.23
    åĽ½æ°ijç»ıæµİ
    -0.23
     bergen
    -0.23
    DataAdapter
    -0.22
    POSITIVE LOGITS
    lining
    0.27
    uating
    0.25
    uali
    0.24
    umm
    0.24
    ALE
    0.24
    Solo
    0.23
     slim
    0.23
    tras
    0.23
    )|(
    0.22
    ANE
    0.22
    Activations Density 0.297%

    No Known Activations

    This feature has no known activations.