© 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. 5055
    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
    åħļåĨħ
    -0.29
     vant
    -0.27
    gatsby
    -0.26
     gate
    -0.26
    ansa
    -0.25
    å¹Ķ
    -0.25
    å¹½
    -0.25
    anova
    -0.24
    heck
    -0.24
    润
    -0.24
    POSITIVE LOGITS
    bö
    0.28
    款
    0.26
    æĢ§åĴĮ
    0.26
     THR
    0.25
    ayah
    0.24
    ischer
    0.24
    ç§ī
    0.24
    +'_
    0.24
    åŃķå¦ĩ
    0.24
    糧
    0.24
    Activations Density 0.122%

    No Known Activations

    This feature has no known activations.