© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7462
    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
    èĦ±
    -0.30
    U
    -0.28
    åı¯æĺ¯
    -0.28
     dec
    -0.27
    两级
    -0.27
    çķ¹
    -0.27
    çļĦä¸ĸçķĮ
    -0.27
    çݯå¢ĥ
    -0.27
    é£İä¿Ĺ
    -0.26
    çļĦå¿ĥçIJĨ
    -0.26
    POSITIVE LOGITS
    >Date
    0.28
    ofi
    0.26
     Excellence
    0.25
     benches
    0.25
    itories
    0.23
     Criterion
    0.23
    æī¹åıij
    0.23
    æ°¤
    0.23
     Officials
    0.23
    illation
    0.23
    Activations Density 0.059%

    No Known Activations

    This feature has no known activations.