© 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. 5075
    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
    ä»ĸ们ä¼ļ
    -0.26
    失åĪ©
    -0.26
    lys
    -0.26
    ather
    -0.25
    opard
    -0.24
    她们
    -0.24
    ´Ģ
    -0.24
    ä¹³
    -0.24
     age
    -0.24
    ä»ĸä¼ļ
    -0.23
    POSITIVE LOGITS
    åı¯çĶ¨
    0.28
    .Companion
    0.25
    çĤ¹æ»´
    0.25
     retained
    0.25
    daq
    0.24
    ä¹Łä¸įè¦ģ
    0.24
    tributes
    0.23
    groupBox
    0.23
     nomin
    0.23
    weekly
    0.23
    Activations Density 0.055%

    No Known Activations

    This feature has no known activations.