© 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. 108091
    Prev
    Next
    INDEX
    Explanations

    Technical articles

    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
    人次
    -0.25
    大éĻĨ
    -0.25
    á¹ĩ
    -0.25
    _CLOSED
    -0.24
    å¢ŀèµĦ
    -0.24
     swearing
    -0.24
    ê³µ
    -0.24
    \$
    -0.24
     casualty
    -0.24
    çIJĩ
    -0.24
    POSITIVE LOGITS
    们
    0.32
     UnityEditor
    0.28
    大éĺŁ
    0.28
    åĵªäºĽ
    0.28
    仨
    0.28
    สà¸ĩ
    0.27
    åĩłä¸ª
    0.27
    åĢij
    0.27
    æĿŁ
    0.27
    éĤ£äºĽ
    0.27
    Activations Density 44.733%

    No Known Activations