© 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. 63785
    Prev
    Next
    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    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
    宸
    -0.27
    ä¼ļ被
    -0.26
    åıijå¸ĥæŶéĹ´
    -0.25
    ä¼ļè§īå¾Ĺ
    -0.25
    ä»İä¸Ń
    -0.25
    ël
    -0.25
    cip
    -0.24
     util
    -0.24
    æ¦ľ
    -0.24
    ersion
    -0.24
    POSITIVE LOGITS
    满
    0.32
    ervative
    0.28
    ãģ¾ãģĦ
    0.28
    æĮĩçĿĢ
    0.27
    worthy
    0.26
     sett
    0.26
    以èĩ³äºİ
    0.26
     lined
    0.26
     Haram
    0.25
    éĩıåĮĸ
    0.25
    Activations Density 5.924%

    No Known Activations