© 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. 142033
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    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
    reaction
    -0.24
    åĩŃåĢŁçĿĢ
    -0.24
     Bes
    -0.24
    Authority
    -0.24
    å¯Ĵ
    -0.23
    å°¼æĸ¯
    -0.23
     Hood
    -0.23
    ú
    -0.23
    åĽ¤
    -0.23
    ucid
    -0.23
    POSITIVE LOGITS
    ystate
    0.29
    æĭŁ
    0.25
    æķĪçİĩ
    0.25
    aje
    0.25
    orama
    0.24
    \"",
    0.24
     branches
    0.24
    .pe
    0.23
    Prefs
    0.23
    åŃĹ第
    0.23
    Activations Density 14.732%

    No Known Activations