© 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. 6358
    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
    éļıæľº
    -0.28
     Pitch
    -0.27
    è¿ĩ渡
    -0.26
    æī§
    -0.25
    ZA
    -0.25
    ìº
    -0.24
    IMIZE
    -0.24
    è¿Ļä¸Ģ次
    -0.23
    èĪ«
    -0.23
    äºĭæķħåıijçĶŁ
    -0.23
    POSITIVE LOGITS
    æ°ijéĸĵ
    0.26
    lico
    0.25
     temptation
    0.25
     exploration
    0.24
    ù
    0.23
    unity
    0.23
     ether
    0.23
    çĶ³æĬ¥
    0.23
    aney
    0.23
     пÑĢедоÑģÑĤавлен
    0.22
    Activations Density 0.240%

    No Known Activations

    This feature has no known activations.