© 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. 129557
    Prev
    Next
    INDEX
    Explanations

    Random text 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
    @Configuration
    -0.27
    iveau
    -0.26
    宵
    -0.26
    oord
    -0.25
     Kyoto
    -0.24
     #__
    -0.23
    åĨ³çŃĸ
    -0.23
    çĶŁäº§æĢ»
    -0.23
    öm
    -0.23
    çĨŁ
    -0.23
    POSITIVE LOGITS
    åĭŁ
    0.29
     ling
    0.25
     jub
    0.25
    leÅŁ
    0.25
    ãĦ§
    0.25
    èµ·
    0.24
     atr
    0.24
     должна
    0.24
    ame
    0.24
     bib
    0.24
    Activations Density 0.814%

    No Known Activations