© 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. 107482
    Prev
    Next
    INDEX
    Explanations

    Text snippets/fragments

    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
    æ¹¾
    -0.32
     guise
    -0.24
     linking
    -0.24
     quoi
    -0.24
    clair
    -0.24
    éħ°
    -0.24
    cons
    -0.24
    åĽ½åĨħ
    -0.23
    åľ¨åĽ½åĨħ
    -0.23
     "\\"
    -0.23
    POSITIVE LOGITS
    ä¸įå®ļ
    0.27
    thur
    0.27
    åºĶä»ĺ
    0.27
    èĴ
    0.25
    Dept
    0.25
    rens
    0.25
     enumerator
    0.25
    à¸Ķำ
    0.25
    _SUITE
    0.24
    rott
    0.24
    Activations Density 20.028%

    No Known Activations