© 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. 63116
    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
    æĮ£
    -0.30
    RON
    -0.27
    åĴĮå¹³
    -0.25
    åīĶ
    -0.25
    æĥħèĬĤ
    -0.25
    使å¾Ĺ
    -0.25
    åģ¿
    -0.24
    æĸ©
    -0.24
     POSSIBILITY
    -0.24
    æĻĵ
    -0.24
    POSITIVE LOGITS
    orate
    0.30
    eor
    0.28
    ä¹Łä¸º
    0.27
     excell
    0.26
    odox
    0.25
    纳ç¨İ
    0.25
     mater
    0.24
     cleaners
    0.24
     Haj
    0.24
    è¾ĥ好
    0.24
    Activations Density 0.834%

    No Known Activations

    This feature has no known activations.