© 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. 130051
    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
    æĺ¯æĪij
    -0.25
    _Framework
    -0.24
    hammer
    -0.24
    å®ŀçĶ¨æĢ§
    -0.24
    istra
    -0.23
     initComponents
    -0.23
    æ¡¥
    -0.23
     InitializeComponent
    -0.23
    åĿĬ
    -0.23
     bridge
    -0.22
    POSITIVE LOGITS
    æ§Ľ
    0.28
    avian
    0.27
    uplicates
    0.26
    æµ´
    0.25
    loat
    0.25
    lessly
    0.24
    orate
    0.24
    ä¾µèļĢ
    0.24
    verige
    0.24
    cznie
    0.24
    Activations Density 63.228%

    No Known Activations

    This feature has no known activations.