© 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. 141222
    Prev
    Next
    INDEX
    Explanations

    girls and boys

    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
    ĶåĽŀ
    -0.29
    jour
    -0.26
    plied
    -0.26
    adal
    -0.25
    ảo
    -0.25
    جز
    -0.24
    ç²ĴåŃIJ
    -0.24
    /></
    -0.24
    ozy
    -0.24
    åľºåĿĩ
    -0.24
    POSITIVE LOGITS
    太å°ij
    0.28
    Money
    0.26
     money
    0.26
    æĢĸ
    0.25
     tav
    0.25
    ä¸ŃéĢĶ
    0.25
    è¿ĩ大
    0.24
    s
    0.24
    æĬĽå¼ĥ
    0.24
     outside
    0.24
    Activations Density 13.165%

    No Known Activations