© 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. 32-TRANSCODER-HP
    7. 42876
    Prev
    Next
    INDEX
    Explanations

    Non-English code and text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -0.39
    æĿ¥è¿Ľè¡Į
    -0.32
    è¦ģ
    -0.28
    æĸ¹å¼ıè¿Ľè¡Į
    -0.27
    æĿ¥è®²
    -0.27
    ä¸įåĥı
    -0.26
    çļĦæĸ¹å¼ıæĿ¥
    -0.26
     tun
    -0.26
    è¦ģæĬĬ
    -0.26
    è¦ģåĬłå¼º
    -0.26
    POSITIVE LOGITS
     Ãł
    0.65
     Ãłs
    0.60
     aos
    0.59
     au
    0.56
     at
    0.55
    Ãł
    0.51
     alla
    0.51
     aux
    0.50
    äºİ
    0.47
    åĪ°äºĨ
    0.47
    Activations Density 0.004%

    No Known Activations