© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8273
    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
    å±ĢéĻIJ
    -0.29
    æľ«
    -0.28
    éĻIJå®ļ
    -0.26
    ascar
    -0.26
    尽头
    -0.26
    éĢģåİ»
    -0.26
    æľ«ç«¯
    -0.26
    å¾ħ
    -0.24
    æĹĥ
    -0.24
    leetcode
    -0.24
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.28
    adge
    0.27
    hra
    0.27
    èĥ½è¾¾åĪ°
    0.26
    åĢij
    0.25
    åıĪèĥ½
    0.24
    ogeneity
    0.24
    æ±īæĹı
    0.24
    说èĩªå·±
    0.24
     Stations
    0.24
    Activations Density 0.170%

    No Known Activations

    This feature has no known activations.