© 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. 6304
    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
    aul
    -0.28
    åĪ°è´¦
    -0.27
    entials
    -0.27
    ÃĹ↵↵
    -0.27
    (active
    -0.27
    ->↵
    -0.26
    è®°ä½ı
    -0.26
     remember
    -0.26
    ãĥķãĥ«
    -0.26
    è®°å¾Ĺ
    -0.25
    POSITIVE LOGITS
    -dev
    0.27
    pres
    0.25
    Pres
    0.25
    /apt
    0.25
    oint
    0.25
    -pres
    0.25
    fav
    0.25
    ä¸Ģæł·çļĦ
    0.24
    åĢĴ
    0.24
    edReader
    0.23
    Activations Density 0.276%

    No Known Activations

    This feature has no known activations.