© 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. 6951
    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
    æ¯ĴæĢ§
    -0.33
     diret
    -0.29
    移åĬ¨
    -0.28
    éĵ¾
    -0.28
    æ¯Ĵ
    -0.28
     dir
    -0.27
    妲
    -0.26
    è¿ģ移
    -0.26
     multip
    -0.25
    Chain
    -0.25
    POSITIVE LOGITS
    æĸ¹æĸ¹éĿ¢
    0.28
    nev
    0.26
     Parade
    0.25
    è¦ģä¸įçĦ¶
    0.25
     "..
    0.24
    ongo
    0.24
    æĥħ人
    0.24
    inan
    0.23
    rush
    0.23
    éĥ¨åĪĨåľ°åĮº
    0.23
    Activations Density 0.631%

    No Known Activations

    This feature has no known activations.