© 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. 108106
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    åĥı
    -0.28
    æİĪ课
    -0.27
     diagon
    -0.26
    çIJ®
    -0.24
     ba
    -0.24
    æķĻåѦ
    -0.24
    /popper
    -0.24
     пÑĢ
    -0.24
    å®ļä»·
    -0.24
    .UnitTesting
    -0.23
    POSITIVE LOGITS
     limits
    0.56
     limit
    0.54
    ä¸ĬéĻIJ
    0.52
     Limits
    0.51
    éĻIJé¢Ŀ
    0.50
    limit
    0.48
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.48
     limitation
    0.48
    Limits
    0.48
    limits
    0.47
    Activations Density 26.350%

    No Known Activations