© 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. 6228
    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
    æĿµ
    -0.27
    ä¸Ģè½®
    -0.27
    indle
    -0.26
    åĽŀ顾
    -0.26
    ût
    -0.25
     jury
    -0.25
     expectedResult
    -0.25
    osex
    -0.25
    è¿ĺè®°å¾Ĺ
    -0.25
    agine
    -0.24
    POSITIVE LOGITS
    enth
    0.27
    çļĦæĦŁæĥħ
    0.25
    ISTA
    0.24
    åij½
    0.24
    keiten
    0.23
    åºľ
    0.23
    EMPL
    0.23
    大人
    0.22
    ä¹ĥèĩ³
    0.22
     Vet
    0.22
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.