© 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. 4958
    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
     electronically
    -0.25
     typed
    -0.25
    rikes
    -0.24
     degree
    -0.24
    myfile
    -0.24
    Typed
    -0.24
     propagated
    -0.24
    æĮĤ
    -0.24
     CSL
    -0.24
    ä¸İåħ¶ä»ĸ
    -0.24
    POSITIVE LOGITS
    åģľä¸ĭæĿ¥
    0.28
    ız
    0.28
    åİĿ
    0.27
    åĨįæĿ¥
    0.26
     Su
    0.25
     inhibit
    0.25
    zac
    0.25
    enti
    0.24
    ä¸ºæł¸å¿ĥ
    0.24
    ipy
    0.24
    Activations Density 0.065%

    No Known Activations

    This feature has no known activations.