© 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. 141348
    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
     cess
    -0.24
    ä¼ļéķ¿
    -0.23
    mai
    -0.23
    çŁ³çģ°
    -0.23
    adden
    -0.23
    lsen
    -0.23
    解æĶ¾
    -0.23
    åIJĮèĥŀ
    -0.23
     temporary
    -0.22
    ä¸ĢæŶ
    -0.22
    POSITIVE LOGITS
    èĥİ
    0.30
    äºŃ
    0.27
    åĽ¢
    0.27
    LOBAL
    0.26
    tings
    0.26
    +E
    0.25
    pants
    0.24
    åħ¶ä¸Ńæľī
    0.24
    -offset
    0.24
     genetically
    0.24
    Activations Density 1.188%

    No Known Activations

    This feature has no known activations.