© 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. 129892
    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
    çĽ¯çĿĢ
    -0.27
    主ä½ĵ责任
    -0.25
    æ¸ij
    -0.23
     Sovere
    -0.23
    inspect
    -0.23
    unto
    -0.23
     aspiration
    -0.23
    åij¼ãģ°
    -0.23
    åĽłä¸ºå®ĥ
    -0.23
     mama
    -0.23
    POSITIVE LOGITS
     ad
    0.29
    -hover
    0.26
    lingen
    0.26
    ements
    0.25
    ç»
    0.25
    æĹĨ
    0.24
     taraf
    0.24
     Pract
    0.23
    éĺ¶
    0.23
    CP
    0.23
    Activations Density 2.425%

    No Known Activations

    This feature has no known activations.