© 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. 9-TRANSCODER-HP
    7. 29731
    Prev
    Next
    INDEX
    Explanations

    aging, "sen" terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¦ĸ
    -0.27
    âį¨
    -0.26
    (*(
    -0.25
    æģ¯
    -0.25
     cÃł
    -0.24
    |%
    -0.24
    енно
    -0.24
    ssc
    -0.24
    antal
    -0.23
     REGION
    -0.23
    POSITIVE LOGITS
     dot
    0.32
    Dot
    0.28
    dot
    0.26
    -less
    0.26
     Dot
    0.26
    onomy
    0.26
     purs
    0.25
    ç«Ļéķ¿
    0.25
    .Dot
    0.25
    æĹłæĥħ
    0.25
    Activations Density 2.271%

    No Known Activations