© 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. 20-TRANSCODER-HP
    7. 108012
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.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表示
    -0.30
    teenth
    -0.27
    uters
    -0.26
     ва
    -0.26
    她说
    -0.24
    åIJ»
    -0.23
    forget
    -0.23
     Ga
    -0.23
    éĻŁ
    -0.23
    dependent
    -0.22
    POSITIVE LOGITS
     zwar
    0.27
    缴åĪ°
    0.25
     brink
    0.25
    庸
    0.24
    TableWidgetItem
    0.23
    çļĦ人çĶŁ
    0.23
    toArray
    0.23
    æĸ
    0.23
    ä¸įèĥ½åĨį
    0.23
    ä¸Ģ缴åĪ°
    0.23
    Activations Density 39.915%

    No Known Activations

    This feature has no known activations.