© 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. 129398
    Prev
    Next
    INDEX
    Explanations

    Long texts

    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
    é£İéĻ©ç®¡çIJĨ
    -0.30
    itect
    -0.29
     /↵↵
    -0.29
    身形
    -0.28
     /↵
    -0.26
    çļĦé£İéĻ©
    -0.26
    åĽ¾å½¢
    -0.26
     Paras
    -0.26
    paRepository
    -0.25
    ÃŃsticas
    -0.24
    POSITIVE LOGITS
    IsNull
    0.26
    央
    0.26
    /*@
    0.24
    æĪªæŃ¢
    0.23
    ffer
    0.23
     %(
    0.23
     Asked
    0.23
    ASK
    0.23
    å¤ĩ
    0.22
    -Jan
    0.22
    Activations Density 38.670%

    No Known Activations